diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml index 977d8da1..90fef6e5 100644 --- a/.github/workflows/test.yaml +++ b/.github/workflows/test.yaml @@ -126,7 +126,7 @@ jobs: strategy: matrix: rocm-version: - - '6.1.1' + - '6.1.2' runs-on: linux container: rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }} steps: diff --git a/Dockerfile b/Dockerfile index b2c5c4a2..ca393496 100644 --- a/Dockerfile +++ b/Dockerfile @@ -2,7 +2,7 @@ ARG GOLANG_VERSION=1.22.1 ARG CMAKE_VERSION=3.22.1 # this CUDA_VERSION corresponds with the one specified in docs/gpu.md ARG CUDA_VERSION=11.3.1 -ARG ROCM_VERSION=6.1.1 +ARG ROCM_VERSION=6.1.2 # Copy the minimal context we need to run the generate scripts FROM scratch AS llm-code diff --git a/README.md b/README.md index 4399a9df..6157e7ed 100644 --- a/README.md +++ b/README.md @@ -312,6 +312,8 @@ See the [API documentation](./docs/api.md) for all endpoints. - [LLocal.in](https://github.com/kartikm7/llocal) (Easy to use Electron Desktop Client for Ollama) - [Ollama with Google Mesop](https://github.com/rapidarchitect/ollama_mesop/) (Mesop Chat Client implementation with Ollama) - [Kerlig AI](https://www.kerlig.com/) (AI writing assistant for macOS) +- [AI Studio](https://github.com/MindWorkAI/AI-Studio) +- [Sidellama](https://github.com/gyopak/sidellama) (browser-based LLM client) ### Terminal diff --git a/api/client.go b/api/client.go index fccbc9ad..c59fbc42 100644 --- a/api/client.go +++ b/api/client.go @@ -347,7 +347,16 @@ func (c *Client) Heartbeat(ctx context.Context) error { return nil } -// Embeddings generates embeddings from a model. +// Embed generates embeddings from a model. +func (c *Client) Embed(ctx context.Context, req *EmbedRequest) (*EmbedResponse, error) { + var resp EmbedResponse + if err := c.do(ctx, http.MethodPost, "/api/embed", req, &resp); err != nil { + return nil, err + } + return &resp, nil +} + +// Embeddings generates an embedding from a model. func (c *Client) Embeddings(ctx context.Context, req *EmbeddingRequest) (*EmbeddingResponse, error) { var resp EmbeddingResponse if err := c.do(ctx, http.MethodPost, "/api/embeddings", req, &resp); err != nil { diff --git a/api/types.go b/api/types.go index 87844c67..65a99c76 100644 --- a/api/types.go +++ b/api/types.go @@ -47,6 +47,9 @@ type GenerateRequest struct { // Prompt is the textual prompt to send to the model. Prompt string `json:"prompt"` + // Suffix is the text that comes after the inserted text. + Suffix string `json:"suffix"` + // System overrides the model's default system message/prompt. System string `json:"system"` @@ -97,17 +100,80 @@ type ChatRequest struct { // followin the request. KeepAlive *Duration `json:"keep_alive,omitempty"` + // Tools is an optional list of tools the model has access to. + Tools `json:"tools,omitempty"` + // Options lists model-specific options. Options map[string]interface{} `json:"options"` } +type Tools []Tool + +func (t Tools) String() string { + bts, _ := json.Marshal(t) + return string(bts) +} + // Message is a single message in a chat sequence. The message contains the // role ("system", "user", or "assistant"), the content and an optional list // of images. type Message struct { - Role string `json:"role"` - Content string `json:"content"` - Images []ImageData `json:"images,omitempty"` + Role string `json:"role"` + Content string `json:"content"` + Images []ImageData `json:"images,omitempty"` + ToolCalls []ToolCall `json:"tool_calls,omitempty"` +} + +func (m *Message) UnmarshalJSON(b []byte) error { + type Alias Message + var a Alias + if err := json.Unmarshal(b, &a); err != nil { + return err + } + + *m = Message(a) + m.Role = strings.ToLower(m.Role) + return nil +} + +type ToolCall struct { + Function ToolCallFunction `json:"function"` +} + +type ToolCallFunction struct { + Name string `json:"name"` + Arguments ToolCallFunctionArguments `json:"arguments"` +} + +type ToolCallFunctionArguments map[string]any + +func (t *ToolCallFunctionArguments) String() string { + bts, _ := json.Marshal(t) + return string(bts) +} + +type Tool struct { + Type string `json:"type"` + Function ToolFunction `json:"function"` +} + +type ToolFunction struct { + Name string `json:"name"` + Description string `json:"description"` + Parameters struct { + Type string `json:"type"` + Required []string `json:"required"` + Properties map[string]struct { + Type string `json:"type"` + Description string `json:"description"` + Enum []string `json:"enum,omitempty"` + } `json:"properties"` + } `json:"parameters"` +} + +func (t *ToolFunction) String() string { + bts, _ := json.Marshal(t) + return string(bts) } // ChatResponse is the response returned by [Client.Chat]. Its fields are @@ -173,6 +239,30 @@ type Runner struct { NumThread int `json:"num_thread,omitempty"` } +// EmbedRequest is the request passed to [Client.Embed]. +type EmbedRequest struct { + // Model is the model name. + Model string `json:"model"` + + // Input is the input to embed. + Input any `json:"input"` + + // KeepAlive controls how long the model will stay loaded in memory following + // this request. + KeepAlive *Duration `json:"keep_alive,omitempty"` + + Truncate *bool `json:"truncate,omitempty"` + + // Options lists model-specific options. + Options map[string]interface{} `json:"options"` +} + +// EmbedResponse is the response from [Client.Embed]. +type EmbedResponse struct { + Model string `json:"model"` + Embeddings [][]float32 `json:"embeddings"` +} + // EmbeddingRequest is the request passed to [Client.Embeddings]. type EmbeddingRequest struct { // Model is the model name. @@ -219,8 +309,10 @@ type DeleteRequest struct { // ShowRequest is the request passed to [Client.Show]. type ShowRequest struct { - Model string `json:"model"` - System string `json:"system"` + Model string `json:"model"` + System string `json:"system"` + + // Template is deprecated Template string `json:"template"` Verbose bool `json:"verbose"` diff --git a/api/types_test.go b/api/types_test.go index c60ed90e..4699c150 100644 --- a/api/types_test.go +++ b/api/types_test.go @@ -208,3 +208,26 @@ func TestUseMmapFormatParams(t *testing.T) { }) } } + +func TestMessage_UnmarshalJSON(t *testing.T) { + tests := []struct { + input string + expected string + }{ + {`{"role": "USER", "content": "Hello!"}`, "user"}, + {`{"role": "System", "content": "Initialization complete."}`, "system"}, + {`{"role": "assistant", "content": "How can I help you?"}`, "assistant"}, + {`{"role": "TOOl", "content": "Access granted."}`, "tool"}, + } + + for _, test := range tests { + var msg Message + if err := json.Unmarshal([]byte(test.input), &msg); err != nil { + t.Errorf("Unexpected error: %v", err) + } + + if msg.Role != test.expected { + t.Errorf("role not lowercased: got %v, expected %v", msg.Role, test.expected) + } + } +} diff --git a/app/lifecycle/updater.go b/app/lifecycle/updater.go index b6d95330..de2cbe77 100644 --- a/app/lifecycle/updater.go +++ b/app/lifecycle/updater.go @@ -23,7 +23,7 @@ import ( ) var ( - UpdateCheckURLBase = "https://ollama.com/api/update" + UpdateCheckURLBase = "https://api.github.com/repos/likelovewant/ollama-for-amd/releases/latest" UpdateDownloaded = false UpdateCheckInterval = 60 * 60 * time.Second ) diff --git a/cmd/cmd.go b/cmd/cmd.go index c898c7db..2252a905 100644 --- a/cmd/cmd.go +++ b/cmd/cmd.go @@ -843,7 +843,6 @@ type runOptions struct { WordWrap bool Format string System string - Template string Images []api.ImageData Options map[string]interface{} MultiModal bool @@ -1037,7 +1036,6 @@ func generate(cmd *cobra.Command, opts runOptions) error { Images: opts.Images, Format: opts.Format, System: opts.System, - Template: opts.Template, Options: opts.Options, KeepAlive: opts.KeepAlive, } diff --git a/cmd/interactive.go b/cmd/interactive.go index 9214f2db..adbc3e9f 100644 --- a/cmd/interactive.go +++ b/cmd/interactive.go @@ -27,7 +27,6 @@ const ( MultilineNone MultilineState = iota MultilinePrompt MultilineSystem - MultilineTemplate ) func loadModel(cmd *cobra.Command, opts *runOptions) error { @@ -94,7 +93,6 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { fmt.Fprintln(os.Stderr, "Available Commands:") fmt.Fprintln(os.Stderr, " /set parameter ... Set a parameter") fmt.Fprintln(os.Stderr, " /set system Set system message") - fmt.Fprintln(os.Stderr, " /set template Set prompt template") fmt.Fprintln(os.Stderr, " /set history Enable history") fmt.Fprintln(os.Stderr, " /set nohistory Disable history") fmt.Fprintln(os.Stderr, " /set wordwrap Enable wordwrap") @@ -204,10 +202,6 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { opts.Messages = append(opts.Messages, api.Message{Role: "system", Content: opts.System}) fmt.Println("Set system message.") sb.Reset() - case MultilineTemplate: - opts.Template = sb.String() - fmt.Println("Set prompt template.") - sb.Reset() } multiline = MultilineNone @@ -326,17 +320,13 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { } fmt.Printf("Set parameter '%s' to '%s'\n", args[2], strings.Join(params, ", ")) opts.Options[args[2]] = fp[args[2]] - case "system", "template": + case "system": if len(args) < 3 { usageSet() continue } - if args[1] == "system" { - multiline = MultilineSystem - } else if args[1] == "template" { - multiline = MultilineTemplate - } + multiline = MultilineSystem line := strings.Join(args[2:], " ") line, ok := strings.CutPrefix(line, `"""`) @@ -356,23 +346,17 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { continue } - if args[1] == "system" { - opts.System = sb.String() // for display in modelfile - newMessage := api.Message{Role: "system", Content: sb.String()} - // Check if the slice is not empty and the last message is from 'system' - if len(opts.Messages) > 0 && opts.Messages[len(opts.Messages)-1].Role == "system" { - // Replace the last message - opts.Messages[len(opts.Messages)-1] = newMessage - } else { - opts.Messages = append(opts.Messages, newMessage) - } - fmt.Println("Set system message.") - sb.Reset() - } else if args[1] == "template" { - opts.Template = sb.String() - fmt.Println("Set prompt template.") - sb.Reset() + opts.System = sb.String() // for display in modelfile + newMessage := api.Message{Role: "system", Content: sb.String()} + // Check if the slice is not empty and the last message is from 'system' + if len(opts.Messages) > 0 && opts.Messages[len(opts.Messages)-1].Role == "system" { + // Replace the last message + opts.Messages[len(opts.Messages)-1] = newMessage + } else { + opts.Messages = append(opts.Messages, newMessage) } + fmt.Println("Set system message.") + sb.Reset() sb.Reset() continue @@ -393,7 +377,6 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { req := &api.ShowRequest{ Name: opts.Model, System: opts.System, - Template: opts.Template, Options: opts.Options, } resp, err := client.Show(cmd.Context(), req) @@ -437,12 +420,9 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error { fmt.Println("No system message was specified for this model.") } case "template": - switch { - case opts.Template != "": - fmt.Println(opts.Template + "\n") - case resp.Template != "": + if resp.Template != "" { fmt.Println(resp.Template) - default: + } else { fmt.Println("No prompt template was specified for this model.") } default: @@ -536,10 +516,6 @@ func buildModelfile(opts runOptions) string { fmt.Fprintf(&mf, "SYSTEM \"\"\"%s\"\"\"\n", opts.System) } - if opts.Template != "" { - fmt.Fprintf(&mf, "TEMPLATE \"\"\"%s\"\"\"\n", opts.Template) - } - keys := make([]string, 0) for k := range opts.Options { keys = append(keys, k) diff --git a/cmd/interactive_test.go b/cmd/interactive_test.go index d9af01eb..711f3860 100644 --- a/cmd/interactive_test.go +++ b/cmd/interactive_test.go @@ -59,7 +59,6 @@ func TestModelfileBuilder(t *testing.T) { opts := runOptions{ Model: "hork", System: "You are part horse and part shark, but all hork. Do horklike things", - Template: "This is a template.", Messages: []api.Message{ {Role: "user", Content: "Hey there hork!"}, {Role: "assistant", Content: "Yes it is true, I am half horse, half shark."}, @@ -75,7 +74,6 @@ func TestModelfileBuilder(t *testing.T) { mf := buildModelfile(opts) expectedModelfile := `FROM {{.Model}} SYSTEM """{{.System}}""" -TEMPLATE """{{.Template}}""" PARAMETER penalize_newline false PARAMETER seed 42 PARAMETER stop [hi there] @@ -97,7 +95,6 @@ MESSAGE assistant """Yes it is true, I am half horse, half shark.""" mf = buildModelfile(opts) expectedModelfile = `FROM {{.ParentModel}} SYSTEM """{{.System}}""" -TEMPLATE """{{.Template}}""" PARAMETER penalize_newline false PARAMETER seed 42 PARAMETER stop [hi there] diff --git a/docs/openai.md b/docs/openai.md index 9dda05c3..248ba74a 100644 --- a/docs/openai.md +++ b/docs/openai.md @@ -103,10 +103,6 @@ curl http://localhost:11434/v1/chat/completions \ - [ ] `user` - [ ] `n` -#### Notes - -- `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached - ## Models Before using a model, pull it locally `ollama pull`: diff --git a/integration/embed_test.go b/integration/embed_test.go new file mode 100644 index 00000000..aeafa57b --- /dev/null +++ b/integration/embed_test.go @@ -0,0 +1,152 @@ +//go:build integration + +package integration + +import ( + "context" + "testing" + "time" + + "github.com/ollama/ollama/api" +) + +func TestAllMiniLMEmbed(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute) + defer cancel() + + req := api.EmbedRequest{ + Model: "all-minilm", + Input: "why is the sky blue?", + } + + res, err := embedTestHelper(ctx, t, req) + + if err != nil { + t.Fatalf("error: %v", err) + } + + if len(res.Embeddings) != 1 { + t.Fatalf("expected 1 embedding, got %d", len(res.Embeddings)) + } + + if len(res.Embeddings[0]) != 384 { + t.Fatalf("expected 384 floats, got %d", len(res.Embeddings[0])) + } + + if res.Embeddings[0][0] != 0.010071031 { + t.Fatalf("expected 0.010071031, got %f", res.Embeddings[0][0]) + } +} + +func TestAllMiniLMBatchEmbed(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute) + defer cancel() + + req := api.EmbedRequest{ + Model: "all-minilm", + Input: []string{"why is the sky blue?", "why is the grass green?"}, + } + + res, err := embedTestHelper(ctx, t, req) + + if err != nil { + t.Fatalf("error: %v", err) + } + + if len(res.Embeddings) != 2 { + t.Fatalf("expected 2 embeddings, got %d", len(res.Embeddings)) + } + + if len(res.Embeddings[0]) != 384 { + t.Fatalf("expected 384 floats, got %d", len(res.Embeddings[0])) + } + + if res.Embeddings[0][0] != 0.010071031 || res.Embeddings[1][0] != -0.009802706 { + t.Fatalf("expected 0.010071031 and -0.009802706, got %f and %f", res.Embeddings[0][0], res.Embeddings[1][0]) + } +} + +func TestAllMiniLmEmbedTruncate(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute) + defer cancel() + + truncTrue, truncFalse := true, false + + type testReq struct { + Name string + Request api.EmbedRequest + } + + reqs := []testReq{ + { + Name: "Target Truncation", + Request: api.EmbedRequest{ + Model: "all-minilm", + Input: "why", + }, + }, + { + Name: "Default Truncate", + Request: api.EmbedRequest{ + Model: "all-minilm", + Input: "why is the sky blue?", + Options: map[string]any{"num_ctx": 1}, + }, + }, + { + Name: "Explicit Truncate", + Request: api.EmbedRequest{ + Model: "all-minilm", + Input: "why is the sky blue?", + Truncate: &truncTrue, + Options: map[string]any{"num_ctx": 1}, + }, + }, + } + + res := make(map[string]*api.EmbedResponse) + + for _, req := range reqs { + response, err := embedTestHelper(ctx, t, req.Request) + if err != nil { + t.Fatalf("error: %v", err) + } + res[req.Name] = response + } + + if res["Target Truncation"].Embeddings[0][0] != res["Default Truncate"].Embeddings[0][0] { + t.Fatal("expected default request to truncate correctly") + } + + if res["Default Truncate"].Embeddings[0][0] != res["Explicit Truncate"].Embeddings[0][0] { + t.Fatal("expected default request and truncate true request to be the same") + } + + // check that truncate set to false returns an error if context length is exceeded + _, err := embedTestHelper(ctx, t, api.EmbedRequest{ + Model: "all-minilm", + Input: "why is the sky blue?", + Truncate: &truncFalse, + Options: map[string]any{"num_ctx": 1}, + }) + + if err == nil { + t.Fatal("expected error, got nil") + } +} + +func embedTestHelper(ctx context.Context, t *testing.T, req api.EmbedRequest) (*api.EmbedResponse, error) { + client, _, cleanup := InitServerConnection(ctx, t) + defer cleanup() + if err := PullIfMissing(ctx, client, req.Model); err != nil { + t.Fatalf("failed to pull model %s: %v", req.Model, err) + } + + response, err := client.Embed(ctx, &req) + + if err != nil { + return nil, err + } + + return response, nil +} diff --git a/llm/ext_server/server.cpp b/llm/ext_server/server.cpp index 0ef3956e..e8a076c4 100644 --- a/llm/ext_server/server.cpp +++ b/llm/ext_server/server.cpp @@ -3188,26 +3188,33 @@ int main(int argc, char **argv) { prompt = ""; } - json image_data; - if (body.count("image_data") != 0) { - image_data = body["image_data"]; - } - else - { - image_data = ""; + if (prompt.size() == 1) { + prompt = prompt[0]; } // create and queue the task - const int task_id = llama.queue_tasks.get_new_id(); - llama.queue_results.add_waiting_task_id(task_id); - llama.request_completion(task_id, { {"prompt", prompt}, { "n_predict", 0}, {"image_data", image_data} }, true, -1); + json responses; + { + const int id_task = llama.queue_tasks.get_new_id(); + llama.queue_results.add_waiting_task_id(id_task); + llama.request_completion(id_task, {{"prompt", prompt}}, true, -1); - // get the result - task_result result = llama.queue_results.recv(task_id); - llama.queue_results.remove_waiting_task_id(task_id); + // get the result + task_result result = llama.queue_results.recv(id_task); + llama.queue_results.remove_waiting_task_id(id_task); + if (result.error) { + return res.set_content(result.result_json.dump(), "application/json; charset=utf-8"); + } - // send the result - return res.set_content(result.result_json.dump(), "application/json; charset=utf-8"); + responses = result.result_json.value("results", std::vector{result.result_json}); + json embeddings = json::array(); + for (auto & elem : responses) { + embeddings.push_back(elem.at("embedding")); + } + // send the result + json embedding_res = json{{"embedding", embeddings}}; + return res.set_content(embedding_res.dump(), "application/json; charset=utf-8"); + } }); // GG: if I put the main loop inside a thread, it crashes on the first request when build in Debug!? diff --git a/llm/generate/gen_windows.ps1 b/llm/generate/gen_windows.ps1 index d146f2f7..bfb6d39d 100644 --- a/llm/generate/gen_windows.ps1 +++ b/llm/generate/gen_windows.ps1 @@ -6,7 +6,7 @@ function amdGPUs { if ($env:AMDGPU_TARGETS) { return $env:AMDGPU_TARGETS } - # Current supported rocblas list from ROCm v6.1.2 on windows + # TODO - load from some common data file for linux + windows build consistency $GPU_LIST = @( "gfx803" "gfx900" @@ -50,8 +50,8 @@ function init_vars { } $script:cmakeDefs = @( "-DBUILD_SHARED_LIBS=on", - "-DGGML_NATIVE=off", - "-DGGML_OPENMP=off" + "-DLLAMA_NATIVE=off", + "-DLLAMA_OPENMP=off" ) $script:commonCpuDefs = @("-DCMAKE_POSITION_INDEPENDENT_CODE=on") $script:ARCH = $Env:PROCESSOR_ARCHITECTURE.ToLower() @@ -193,9 +193,9 @@ function cleanup { } -# -DGGML_AVX -- 2011 Intel Sandy Bridge & AMD Bulldozer -# -DGGML_AVX2 -- 2013 Intel Haswell & 2015 AMD Excavator / 2017 AMD Zen -# -DGGML_FMA (FMA3) -- 2013 Intel Haswell & 2012 AMD Piledriver +# -DLLAMA_AVX -- 2011 Intel Sandy Bridge & AMD Bulldozer +# -DLLAMA_AVX2 -- 2013 Intel Haswell & 2015 AMD Excavator / 2017 AMD Zen +# -DLLAMA_FMA (FMA3) -- 2013 Intel Haswell & 2012 AMD Piledriver function build_static() { @@ -215,13 +215,13 @@ function build_static() { "-DCMAKE_C_COMPILER=gcc.exe", "-DCMAKE_CXX_COMPILER=g++.exe", "-DBUILD_SHARED_LIBS=off", - "-DGGML_NATIVE=off", - "-DGGML_AVX=off", - "-DGGML_AVX2=off", - "-DGGML_AVX512=off", - "-DGGML_F16C=off", - "-DGGML_FMA=off", - "-DGGML_OPENMP=off") + "-DLLAMA_NATIVE=off", + "-DLLAMA_AVX=off", + "-DLLAMA_AVX2=off", + "-DLLAMA_AVX512=off", + "-DLLAMA_F16C=off", + "-DLLAMA_FMA=off", + "-DLLAMA_OPENMP=off") $script:buildDir="../build/windows/${script:ARCH}_static" write-host "Building static library" build @@ -235,7 +235,7 @@ function build_cpu($gen_arch) { if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu"))) { # remaining llama.cpp builds use MSVC init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", $gen_arch, "-DGGML_AVX=off", "-DGGML_AVX2=off", "-DGGML_AVX512=off", "-DGGML_FMA=off", "-DGGML_F16C=off") + $script:cmakeDefs + $script:cmakeDefs = $script:commonCpuDefs + @("-A", $gen_arch, "-DLLAMA_AVX=off", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs $script:buildDir="../build/windows/${script:ARCH}/cpu" $script:distDir="$script:DIST_BASE\cpu" write-host "Building LCD CPU" @@ -250,7 +250,7 @@ function build_cpu($gen_arch) { function build_cpu_avx() { if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu_avx"))) { init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DGGML_AVX=on", "-DGGML_AVX2=off", "-DGGML_AVX512=off", "-DGGML_FMA=off", "-DGGML_F16C=off") + $script:cmakeDefs + $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs $script:buildDir="../build/windows/${script:ARCH}/cpu_avx" $script:distDir="$script:DIST_BASE\cpu_avx" write-host "Building AVX CPU" @@ -265,7 +265,7 @@ function build_cpu_avx() { function build_cpu_avx2() { if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu_avx2"))) { init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DGGML_AVX=on", "-DGGML_AVX2=on", "-DGGML_AVX512=off", "-DGGML_FMA=on", "-DGGML_F16C=on") + $script:cmakeDefs + $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=on", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=on", "-DLLAMA_F16C=on") + $script:cmakeDefs $script:buildDir="../build/windows/${script:ARCH}/cpu_avx2" $script:distDir="$script:DIST_BASE\cpu_avx2" write-host "Building AVX2 CPU" @@ -290,9 +290,9 @@ function build_cuda() { $script:distDir="$script:DIST_BASE\cuda$script:CUDA_VARIANT" $script:cmakeDefs += @( "-A", "x64", - "-DGGML_CUDA=ON", - "-DGGML_AVX=on", - "-DGGML_AVX2=off", + "-DLLAMA_CUDA=ON", + "-DLLAMA_AVX=on", + "-DLLAMA_AVX2=off", "-DCUDAToolkit_INCLUDE_DIR=$script:CUDA_INCLUDE_DIR", "-DCMAKE_CUDA_FLAGS=-t8", "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}" @@ -330,7 +330,7 @@ function build_oneapi() { $script:distDir ="$script:DIST_BASE\oneapi$script:ONEAPI_VARIANT" $script:cmakeDefs += @( "-G", "MinGW Makefiles", - "-DGGML_SYCL=ON", + "-DLLAMA_SYCL=ON", "-DCMAKE_C_COMPILER=icx", "-DCMAKE_CXX_COMPILER=icx", "-DCMAKE_BUILD_TYPE=Release" @@ -376,11 +376,10 @@ function build_rocm() { "-G", "Ninja", "-DCMAKE_C_COMPILER=clang.exe", "-DCMAKE_CXX_COMPILER=clang++.exe", - "-DGGML_HIPBLAS=on", - "-DLLAMA_CUDA_NO_PEER_COPY=on", + "-DLLAMA_HIPBLAS=on", "-DHIP_PLATFORM=amd", - "-DGGML_AVX=on", - "-DGGML_AVX2=off", + "-DLLAMA_AVX=on", + "-DLLAMA_AVX2=off", "-DCMAKE_POSITION_INDEPENDENT_CODE=on", "-DAMDGPU_TARGETS=$(amdGPUs)", "-DGPU_TARGETS=$(amdGPUs)" @@ -406,6 +405,7 @@ function build_rocm() { sign install + # Assumes v5.7, may need adjustments for v6 rm -ea 0 -recurse -force -path "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\" md "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\rocblas\library\" -ea 0 > $null cp "${env:HIP_PATH}\bin\hipblas.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\" diff --git a/llm/gguf.go b/llm/gguf.go index 4d343a1b..a8427aed 100644 --- a/llm/gguf.go +++ b/llm/gguf.go @@ -537,6 +537,7 @@ var ggufKVOrder = map[string][]string{ "tokenizer.ggml.add_bos_token", "tokenizer.ggml.add_eos_token", "tokenizer.chat_template", + "bert.pooling_type", }, } diff --git a/llm/server.go b/llm/server.go index ffed9fc0..36c0e0b5 100644 --- a/llm/server.go +++ b/llm/server.go @@ -33,7 +33,7 @@ type LlamaServer interface { Ping(ctx context.Context) error WaitUntilRunning(ctx context.Context) error Completion(ctx context.Context, req CompletionRequest, fn func(CompletionResponse)) error - Embedding(ctx context.Context, prompt string) ([]float64, error) + Embed(ctx context.Context, input []string) ([][]float32, error) Tokenize(ctx context.Context, content string) ([]int, error) Detokenize(ctx context.Context, tokens []int) (string, error) Close() error @@ -867,15 +867,15 @@ func (s *llmServer) Completion(ctx context.Context, req CompletionRequest, fn fu return nil } -type EmbeddingRequest struct { - Content string `json:"content"` +type EmbedRequest struct { + Content []string `json:"content"` } -type EmbeddingResponse struct { - Embedding []float64 `json:"embedding"` +type EmbedResponse struct { + Embedding [][]float32 `json:"embedding"` } -func (s *llmServer) Embedding(ctx context.Context, prompt string) ([]float64, error) { +func (s *llmServer) Embed(ctx context.Context, input []string) ([][]float32, error) { if err := s.sem.Acquire(ctx, 1); err != nil { slog.Error("Failed to acquire semaphore", "error", err) return nil, err @@ -890,7 +890,7 @@ func (s *llmServer) Embedding(ctx context.Context, prompt string) ([]float64, er return nil, fmt.Errorf("unexpected server status: %s", status.ToString()) } - data, err := json.Marshal(TokenizeRequest{Content: prompt}) + data, err := json.Marshal(EmbedRequest{Content: input}) if err != nil { return nil, fmt.Errorf("error marshaling embed data: %w", err) } @@ -917,7 +917,7 @@ func (s *llmServer) Embedding(ctx context.Context, prompt string) ([]float64, er return nil, fmt.Errorf("%s", body) } - var embedding EmbeddingResponse + var embedding EmbedResponse if err := json.Unmarshal(body, &embedding); err != nil { return nil, fmt.Errorf("unmarshal tokenize response: %w", err) } diff --git a/openai/openai.go b/openai/openai.go index 1707da14..01864e48 100644 --- a/openai/openai.go +++ b/openai/openai.go @@ -3,11 +3,14 @@ package openai import ( "bytes" + "encoding/base64" "encoding/json" "fmt" "io" + "log/slog" "math/rand" "net/http" + "strings" "time" "github.com/gin-gonic/gin" @@ -27,8 +30,9 @@ type ErrorResponse struct { } type Message struct { - Role string `json:"role"` - Content string `json:"content"` + Role string `json:"role"` + Content any `json:"content"` + ToolCalls []ToolCall `json:"tool_calls,omitempty"` } type Choice struct { @@ -59,6 +63,11 @@ type ResponseFormat struct { Type string `json:"type"` } +type EmbedRequest struct { + Input any `json:"input"` + Model string `json:"model"` +} + type ChatCompletionRequest struct { Model string `json:"model"` Messages []Message `json:"messages"` @@ -71,6 +80,7 @@ type ChatCompletionRequest struct { PresencePenalty *float64 `json:"presence_penalty_penalty"` TopP *float64 `json:"top_p"` ResponseFormat *ResponseFormat `json:"response_format"` + Tools []api.Tool `json:"tools"` } type ChatCompletion struct { @@ -104,6 +114,7 @@ type CompletionRequest struct { Stream bool `json:"stream"` Temperature *float32 `json:"temperature"` TopP float32 `json:"top_p"` + Suffix string `json:"suffix"` } type Completion struct { @@ -125,6 +136,15 @@ type CompletionChunk struct { SystemFingerprint string `json:"system_fingerprint"` } +type ToolCall struct { + ID string `json:"id"` + Type string `json:"type"` + Function struct { + Name string `json:"name"` + Arguments string `json:"arguments"` + } `json:"function"` +} + type Model struct { Id string `json:"id"` Object string `json:"object"` @@ -132,11 +152,23 @@ type Model struct { OwnedBy string `json:"owned_by"` } +type Embedding struct { + Object string `json:"object"` + Embedding []float32 `json:"embedding"` + Index int `json:"index"` +} + type ListCompletion struct { Object string `json:"object"` Data []Model `json:"data"` } +type EmbeddingList struct { + Object string `json:"object"` + Data []Embedding `json:"data"` + Model string `json:"model"` +} + func NewError(code int, message string) ErrorResponse { var etype string switch code { @@ -151,7 +183,31 @@ func NewError(code int, message string) ErrorResponse { return ErrorResponse{Error{Type: etype, Message: message}} } +func toolCallId() string { + const letterBytes = "abcdefghijklmnopqrstuvwxyz0123456789" + b := make([]byte, 8) + for i := range b { + b[i] = letterBytes[rand.Intn(len(letterBytes))] + } + return "call_" + strings.ToLower(string(b)) +} + func toChatCompletion(id string, r api.ChatResponse) ChatCompletion { + toolCalls := make([]ToolCall, len(r.Message.ToolCalls)) + for i, tc := range r.Message.ToolCalls { + toolCalls[i].ID = toolCallId() + toolCalls[i].Type = "function" + toolCalls[i].Function.Name = tc.Function.Name + + args, err := json.Marshal(tc.Function.Arguments) + if err != nil { + slog.Error("could not marshall function arguments to json", "error", err) + continue + } + + toolCalls[i].Function.Arguments = string(args) + } + return ChatCompletion{ Id: id, Object: "chat.completion", @@ -160,7 +216,7 @@ func toChatCompletion(id string, r api.ChatResponse) ChatCompletion { SystemFingerprint: "fp_ollama", Choices: []Choice{{ Index: 0, - Message: Message{Role: r.Message.Role, Content: r.Message.Content}, + Message: Message{Role: r.Message.Role, Content: r.Message.Content, ToolCalls: toolCalls}, FinishReason: func(reason string) *string { if len(reason) > 0 { return &reason @@ -169,7 +225,6 @@ func toChatCompletion(id string, r api.ChatResponse) ChatCompletion { }(r.DoneReason), }}, Usage: Usage{ - // TODO: ollama returns 0 for prompt eval if the prompt was cached, but openai returns the actual count PromptTokens: r.PromptEvalCount, CompletionTokens: r.EvalCount, TotalTokens: r.PromptEvalCount + r.EvalCount, @@ -215,7 +270,6 @@ func toCompletion(id string, r api.GenerateResponse) Completion { }(r.DoneReason), }}, Usage: Usage{ - // TODO: ollama returns 0 for prompt eval if the prompt was cached, but openai returns the actual count PromptTokens: r.PromptEvalCount, CompletionTokens: r.EvalCount, TotalTokens: r.PromptEvalCount + r.EvalCount, @@ -260,6 +314,27 @@ func toListCompletion(r api.ListResponse) ListCompletion { } } +func toEmbeddingList(model string, r api.EmbedResponse) EmbeddingList { + if r.Embeddings != nil { + var data []Embedding + for i, e := range r.Embeddings { + data = append(data, Embedding{ + Object: "embedding", + Embedding: e, + Index: i, + }) + } + + return EmbeddingList{ + Object: "list", + Data: data, + Model: model, + } + } + + return EmbeddingList{} +} + func toModel(r api.ShowResponse, m string) Model { return Model{ Id: m, @@ -269,10 +344,78 @@ func toModel(r api.ShowResponse, m string) Model { } } -func fromChatRequest(r ChatCompletionRequest) api.ChatRequest { +func fromChatRequest(r ChatCompletionRequest) (*api.ChatRequest, error) { var messages []api.Message for _, msg := range r.Messages { - messages = append(messages, api.Message{Role: msg.Role, Content: msg.Content}) + switch content := msg.Content.(type) { + case string: + messages = append(messages, api.Message{Role: msg.Role, Content: content}) + case []any: + message := api.Message{Role: msg.Role} + for _, c := range content { + data, ok := c.(map[string]any) + if !ok { + return nil, fmt.Errorf("invalid message format") + } + switch data["type"] { + case "text": + text, ok := data["text"].(string) + if !ok { + return nil, fmt.Errorf("invalid message format") + } + message.Content = text + case "image_url": + var url string + if urlMap, ok := data["image_url"].(map[string]any); ok { + if url, ok = urlMap["url"].(string); !ok { + return nil, fmt.Errorf("invalid message format") + } + } else { + if url, ok = data["image_url"].(string); !ok { + return nil, fmt.Errorf("invalid message format") + } + } + + types := []string{"jpeg", "jpg", "png"} + valid := false + for _, t := range types { + prefix := "data:image/" + t + ";base64," + if strings.HasPrefix(url, prefix) { + url = strings.TrimPrefix(url, prefix) + valid = true + break + } + } + + if !valid { + return nil, fmt.Errorf("invalid image input") + } + + img, err := base64.StdEncoding.DecodeString(url) + if err != nil { + return nil, fmt.Errorf("invalid message format") + } + message.Images = append(message.Images, img) + default: + return nil, fmt.Errorf("invalid message format") + } + } + messages = append(messages, message) + default: + if msg.ToolCalls == nil { + return nil, fmt.Errorf("invalid message content type: %T", content) + } + + toolCalls := make([]api.ToolCall, len(msg.ToolCalls)) + for i, tc := range msg.ToolCalls { + toolCalls[i].Function.Name = tc.Function.Name + err := json.Unmarshal([]byte(tc.Function.Arguments), &toolCalls[i].Function.Arguments) + if err != nil { + return nil, fmt.Errorf("invalid tool call arguments") + } + } + messages = append(messages, api.Message{Role: msg.Role, ToolCalls: toolCalls}) + } } options := make(map[string]interface{}) @@ -323,13 +466,14 @@ func fromChatRequest(r ChatCompletionRequest) api.ChatRequest { format = "json" } - return api.ChatRequest{ + return &api.ChatRequest{ Model: r.Model, Messages: messages, Format: format, Options: options, Stream: &r.Stream, - } + Tools: r.Tools, + }, nil } func fromCompleteRequest(r CompletionRequest) (api.GenerateRequest, error) { @@ -379,6 +523,7 @@ func fromCompleteRequest(r CompletionRequest) (api.GenerateRequest, error) { Prompt: r.Prompt, Options: options, Stream: &r.Stream, + Suffix: r.Suffix, }, nil } @@ -407,6 +552,11 @@ type RetrieveWriter struct { model string } +type EmbedWriter struct { + BaseWriter + model string +} + func (w *BaseWriter) writeError(code int, data []byte) (int, error) { var serr api.StatusError err := json.Unmarshal(data, &serr) @@ -572,6 +722,33 @@ func (w *RetrieveWriter) Write(data []byte) (int, error) { return w.writeResponse(data) } +func (w *EmbedWriter) writeResponse(data []byte) (int, error) { + var embedResponse api.EmbedResponse + err := json.Unmarshal(data, &embedResponse) + + if err != nil { + return 0, err + } + + w.ResponseWriter.Header().Set("Content-Type", "application/json") + err = json.NewEncoder(w.ResponseWriter).Encode(toEmbeddingList(w.model, embedResponse)) + + if err != nil { + return 0, err + } + + return len(data), nil +} + +func (w *EmbedWriter) Write(data []byte) (int, error) { + code := w.ResponseWriter.Status() + if code != http.StatusOK { + return w.writeError(code, data) + } + + return w.writeResponse(data) +} + func ListMiddleware() gin.HandlerFunc { return func(c *gin.Context) { w := &ListWriter{ @@ -635,6 +812,47 @@ func CompletionsMiddleware() gin.HandlerFunc { id: fmt.Sprintf("cmpl-%d", rand.Intn(999)), } + c.Writer = w + c.Next() + } +} + +func EmbeddingsMiddleware() gin.HandlerFunc { + return func(c *gin.Context) { + var req EmbedRequest + err := c.ShouldBindJSON(&req) + if err != nil { + c.AbortWithStatusJSON(http.StatusBadRequest, NewError(http.StatusBadRequest, err.Error())) + return + } + + if req.Input == "" { + req.Input = []string{""} + } + + if req.Input == nil { + c.AbortWithStatusJSON(http.StatusBadRequest, NewError(http.StatusBadRequest, "invalid input")) + return + } + + if v, ok := req.Input.([]any); ok && len(v) == 0 { + c.AbortWithStatusJSON(http.StatusBadRequest, NewError(http.StatusBadRequest, "invalid input")) + return + } + + var b bytes.Buffer + if err := json.NewEncoder(&b).Encode(api.EmbedRequest{Model: req.Model, Input: req.Input}); err != nil { + c.AbortWithStatusJSON(http.StatusInternalServerError, NewError(http.StatusInternalServerError, err.Error())) + return + } + + c.Request.Body = io.NopCloser(&b) + + w := &EmbedWriter{ + BaseWriter: BaseWriter{ResponseWriter: c.Writer}, + model: req.Model, + } + c.Writer = w c.Next() @@ -656,7 +874,13 @@ func ChatMiddleware() gin.HandlerFunc { } var b bytes.Buffer - if err := json.NewEncoder(&b).Encode(fromChatRequest(req)); err != nil { + + chatReq, err := fromChatRequest(req) + if err != nil { + c.AbortWithStatusJSON(http.StatusBadRequest, NewError(http.StatusBadRequest, err.Error())) + } + + if err := json.NewEncoder(&b).Encode(chatReq); err != nil { c.AbortWithStatusJSON(http.StatusInternalServerError, NewError(http.StatusInternalServerError, err.Error())) return } diff --git a/openai/openai_test.go b/openai/openai_test.go index 5f1ae52e..046ee69c 100644 --- a/openai/openai_test.go +++ b/openai/openai_test.go @@ -2,6 +2,7 @@ package openai import ( "bytes" + "encoding/base64" "encoding/json" "io" "net/http" @@ -15,6 +16,10 @@ import ( "github.com/stretchr/testify/assert" ) +const prefix = `data:image/jpeg;base64,` +const image = `iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=` +const imageURL = prefix + image + func TestMiddlewareRequests(t *testing.T) { type testCase struct { Name string @@ -80,6 +85,7 @@ func TestMiddlewareRequests(t *testing.T) { Prompt: "Hello", Temperature: &temp, Stop: []string{"\n", "stop"}, + Suffix: "suffix", } bodyBytes, _ := json.Marshal(body) @@ -110,6 +116,126 @@ func TestMiddlewareRequests(t *testing.T) { if stopTokens[0] != "\n" || stopTokens[1] != "stop" { t.Fatalf("expected ['\\n', 'stop'], got %v", stopTokens) } + + if genReq.Suffix != "suffix" { + t.Fatalf("expected 'suffix', got %s", genReq.Suffix) + } + }, + }, + { + Name: "chat handler with image content", + Method: http.MethodPost, + Path: "/api/chat", + Handler: ChatMiddleware, + Setup: func(t *testing.T, req *http.Request) { + body := ChatCompletionRequest{ + Model: "test-model", + Messages: []Message{ + { + Role: "user", Content: []map[string]any{ + {"type": "text", "text": "Hello"}, + {"type": "image_url", "image_url": map[string]string{"url": imageURL}}, + }, + }, + }, + } + + bodyBytes, _ := json.Marshal(body) + + req.Body = io.NopCloser(bytes.NewReader(bodyBytes)) + req.Header.Set("Content-Type", "application/json") + }, + Expected: func(t *testing.T, req *http.Request) { + var chatReq api.ChatRequest + if err := json.NewDecoder(req.Body).Decode(&chatReq); err != nil { + t.Fatal(err) + } + + if chatReq.Messages[0].Role != "user" { + t.Fatalf("expected 'user', got %s", chatReq.Messages[0].Role) + } + + if chatReq.Messages[0].Content != "Hello" { + t.Fatalf("expected 'Hello', got %s", chatReq.Messages[0].Content) + } + + img, _ := base64.StdEncoding.DecodeString(imageURL[len(prefix):]) + + if !bytes.Equal(chatReq.Messages[0].Images[0], img) { + t.Fatalf("expected image encoding, got %s", chatReq.Messages[0].Images[0]) + } + }, + }, + { + Name: "embed handler single input", + Method: http.MethodPost, + Path: "/api/embed", + Handler: EmbeddingsMiddleware, + Setup: func(t *testing.T, req *http.Request) { + body := EmbedRequest{ + Input: "Hello", + Model: "test-model", + } + + bodyBytes, _ := json.Marshal(body) + + req.Body = io.NopCloser(bytes.NewReader(bodyBytes)) + req.Header.Set("Content-Type", "application/json") + }, + Expected: func(t *testing.T, req *http.Request) { + var embedReq api.EmbedRequest + if err := json.NewDecoder(req.Body).Decode(&embedReq); err != nil { + t.Fatal(err) + } + + if embedReq.Input != "Hello" { + t.Fatalf("expected 'Hello', got %s", embedReq.Input) + } + + if embedReq.Model != "test-model" { + t.Fatalf("expected 'test-model', got %s", embedReq.Model) + } + }, + }, + { + Name: "embed handler batch input", + Method: http.MethodPost, + Path: "/api/embed", + Handler: EmbeddingsMiddleware, + Setup: func(t *testing.T, req *http.Request) { + body := EmbedRequest{ + Input: []string{"Hello", "World"}, + Model: "test-model", + } + + bodyBytes, _ := json.Marshal(body) + + req.Body = io.NopCloser(bytes.NewReader(bodyBytes)) + req.Header.Set("Content-Type", "application/json") + }, + Expected: func(t *testing.T, req *http.Request) { + var embedReq api.EmbedRequest + if err := json.NewDecoder(req.Body).Decode(&embedReq); err != nil { + t.Fatal(err) + } + + input, ok := embedReq.Input.([]any) + + if !ok { + t.Fatalf("expected input to be a list") + } + + if input[0].(string) != "Hello" { + t.Fatalf("expected 'Hello', got %s", input[0]) + } + + if input[1].(string) != "World" { + t.Fatalf("expected 'World', got %s", input[1]) + } + + if embedReq.Model != "test-model" { + t.Fatalf("expected 'test-model', got %s", embedReq.Model) + } }, }, } diff --git a/server/images.go b/server/images.go index 688d5dca..5e4e8858 100644 --- a/server/images.go +++ b/server/images.go @@ -34,11 +34,20 @@ import ( "github.com/ollama/ollama/version" ) -var errCapabilityCompletion = errors.New("completion") +var ( + errCapabilities = errors.New("does not support") + errCapabilityCompletion = errors.New("completion") + errCapabilityTools = errors.New("tools") + errCapabilityInsert = errors.New("insert") +) type Capability string -const CapabilityCompletion = Capability("completion") +const ( + CapabilityCompletion = Capability("completion") + CapabilityTools = Capability("tools") + CapabilityInsert = Capability("insert") +) type registryOptions struct { Insecure bool @@ -88,6 +97,15 @@ func (m *Model) CheckCapabilities(caps ...Capability) error { if _, ok := ggml.KV()[fmt.Sprintf("%s.pooling_type", ggml.KV().Architecture())]; ok { errs = append(errs, errCapabilityCompletion) } + case CapabilityTools: + if !slices.Contains(m.Template.Vars(), "tools") { + errs = append(errs, errCapabilityTools) + } + case CapabilityInsert: + vars := m.Template.Vars() + if !slices.Contains(vars, "suffix") { + errs = append(errs, errCapabilityInsert) + } default: slog.Error("unknown capability", "capability", cap) return fmt.Errorf("unknown capability: %s", cap) @@ -95,7 +113,7 @@ func (m *Model) CheckCapabilities(caps ...Capability) error { } if err := errors.Join(errs...); err != nil { - return fmt.Errorf("missing capabilities: %w", errors.Join(errs...)) + return fmt.Errorf("%w %w", errCapabilities, errors.Join(errs...)) } return nil diff --git a/server/model.go b/server/model.go index a79f549a..a084dd8c 100644 --- a/server/model.go +++ b/server/model.go @@ -4,6 +4,7 @@ import ( "archive/zip" "bytes" "context" + "encoding/json" "errors" "fmt" "io" @@ -11,6 +12,9 @@ import ( "net/http" "os" "path/filepath" + "slices" + "strings" + "text/template/parse" "github.com/ollama/ollama/api" "github.com/ollama/ollama/convert" @@ -289,3 +293,92 @@ func detectContentType(r io.Reader) (string, error) { return "unknown", nil } + +// parseToolCalls attempts to parse a JSON string into a slice of ToolCalls. +// mxyng: this only really works if the input contains tool calls in some JSON format +func (m *Model) parseToolCalls(s string) ([]api.ToolCall, bool) { + // create a subtree from the node that ranges over .ToolCalls + tmpl := m.Template.Subtree(func(n parse.Node) bool { + if t, ok := n.(*parse.RangeNode); ok { + return slices.Contains(template.Identifiers(t.Pipe), "ToolCalls") + } + + return false + }) + + if tmpl == nil { + return nil, false + } + + var b bytes.Buffer + if err := tmpl.Execute(&b, map[string][]api.ToolCall{ + "ToolCalls": { + { + Function: api.ToolCallFunction{ + Name: "@@name@@", + Arguments: api.ToolCallFunctionArguments{ + "@@argument@@": 1, + }, + }, + }, + }, + }); err != nil { + return nil, false + } + + var kv map[string]any + // execute the subtree with placeholders to identify the keys + // trim any commands that might exist in the template + if err := json.Unmarshal(bytes.TrimSuffix(b.Bytes(), []byte(",")), &kv); err != nil { + return nil, false + } + + // find the keys that correspond to the name and arguments fields + var name, arguments string + for k, v := range kv { + switch v.(type) { + case string: + name = k + case map[string]any: + arguments = k + } + } + + var objs []map[string]any + for offset := 0; offset < len(s); { + var obj map[string]any + decoder := json.NewDecoder(strings.NewReader(s[offset:])) + if err := decoder.Decode(&obj); errors.Is(err, io.EOF) || errors.Is(err, io.ErrUnexpectedEOF) { + break + } else if syntax := &(json.SyntaxError{}); errors.As(err, &syntax) { + // skip over any syntax errors + offset += int(syntax.Offset) + } else if unmarshalType := &(json.UnmarshalTypeError{}); errors.As(err, &unmarshalType) { + // skip over any unmarshalable types + offset += int(unmarshalType.Offset) + } else if err != nil { + slog.Error("parseToolCalls", "error", err) + return nil, false + } else { + offset += int(decoder.InputOffset()) + objs = append(objs, obj) + } + } + + var toolCalls []api.ToolCall + for _, kv := range objs { + var call api.ToolCall + for k, v := range kv { + switch k { + case name: + call.Function.Name = v.(string) + case arguments: + call.Function.Arguments = v.(map[string]any) + } + } + + toolCalls = append(toolCalls, call) + } + + return toolCalls, len(toolCalls) > 0 +} diff --git a/server/model_test.go b/server/model_test.go index a383b7e7..7c826b06 100644 --- a/server/model_test.go +++ b/server/model_test.go @@ -3,7 +3,9 @@ package server import ( "archive/zip" "bytes" + "encoding/json" "errors" + "fmt" "io" "os" "path/filepath" @@ -11,7 +13,9 @@ import ( "strings" "testing" + "github.com/google/go-cmp/cmp" "github.com/ollama/ollama/api" + "github.com/ollama/ollama/template" ) func createZipFile(t *testing.T, name string) *os.File { @@ -110,3 +114,122 @@ func TestExtractFromZipFile(t *testing.T) { }) } } + +func readFile(t *testing.T, base, name string) *bytes.Buffer { + t.Helper() + + bts, err := os.ReadFile(filepath.Join(base, name)) + if err != nil { + t.Fatal(err) + } + + return bytes.NewBuffer(bts) +} + +func TestExecuteWithTools(t *testing.T) { + p := filepath.Join("testdata", "tools") + cases := []struct { + model string + output string + ok bool + }{ + {"mistral", `[TOOL_CALLS] [{"name": "get_current_weather", "arguments": {"format":"fahrenheit","location":"San Francisco, CA"}},{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Toronto, Canada"}}]`, true}, + {"mistral", `[TOOL_CALLS] [{"name": "get_current_weather", "arguments": {"format":"fahrenheit","location":"San Francisco, CA"}},{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Toronto, Canada"}}] + +The temperature in San Francisco, CA is 70°F and in Toronto, Canada is 20°C.`, true}, + {"mistral", `I'm not aware of that information. However, I can suggest searching for the weather using the "get_current_weather" function: + + [{"name": "get_current_weather", "arguments": {"format":"fahrenheit","location":"San Francisco, CA"}},{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Toronto, Canada"}}]`, true}, + {"mistral", " The weather in San Francisco, CA is 70°F and in Toronto, Canada is 20°C.", false}, + {"command-r-plus", "Action: ```json" + ` +[ + { + "tool_name": "get_current_weather", + "parameters": { + "format": "fahrenheit", + "location": "San Francisco, CA" + } + }, + { + "tool_name": "get_current_weather", + "parameters": { + "format": "celsius", + "location": "Toronto, Canada" + } + } +] +` + "```", true}, + {"command-r-plus", " The weather in San Francisco, CA is 70°F and in Toronto, Canada is 20°C.", false}, + {"firefunction", ` functools[{"name": "get_current_weather", "arguments": {"format":"fahrenheit","location":"San Francisco, CA"}},{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Toronto, Canada"}}]`, true}, + {"firefunction", " The weather in San Francisco, CA is 70°F and in Toronto, Canada is 20°C.", false}, + {"llama3-groq-tool-use", ` +{"name": "get_current_weather", "arguments": {"format":"fahrenheit","location":"San Francisco, CA"}} +{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Toronto, Canada"}} +`, true}, + } + + var tools []api.Tool + if err := json.Unmarshal(readFile(t, p, "tools.json").Bytes(), &tools); err != nil { + t.Fatal(err) + } + + var messages []api.Message + if err := json.Unmarshal(readFile(t, p, "messages.json").Bytes(), &messages); err != nil { + t.Fatal(err) + } + + calls := []api.ToolCall{ + { + Function: api.ToolCallFunction{ + Name: "get_current_weather", + Arguments: api.ToolCallFunctionArguments{ + "format": "fahrenheit", + "location": "San Francisco, CA", + }, + }, + }, + { + Function: api.ToolCallFunction{ + Name: "get_current_weather", + Arguments: api.ToolCallFunctionArguments{ + "format": "celsius", + "location": "Toronto, Canada", + }, + }, + }, + } + + for _, tt := range cases { + t.Run(tt.model, func(t *testing.T) { + tmpl, err := template.Parse(readFile(t, p, fmt.Sprintf("%s.gotmpl", tt.model)).String()) + if err != nil { + t.Fatal(err) + } + + t.Run("template", func(t *testing.T) { + var actual bytes.Buffer + if err := tmpl.Execute(&actual, template.Values{Tools: tools, Messages: messages}); err != nil { + t.Fatal(err) + } + + if diff := cmp.Diff(actual.String(), readFile(t, p, fmt.Sprintf("%s.out", tt.model)).String()); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("parse", func(t *testing.T) { + m := &Model{Template: tmpl} + actual, ok := m.parseToolCalls(tt.output) + if ok != tt.ok { + t.Fatalf("expected %t, got %t", tt.ok, ok) + } + + if tt.ok { + if diff := cmp.Diff(actual, calls); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + } + }) + }) + } +} diff --git a/server/prompt.go b/server/prompt.go index abc5e61e..be0d4969 100644 --- a/server/prompt.go +++ b/server/prompt.go @@ -15,7 +15,7 @@ type tokenizeFunc func(context.Context, string) ([]int, error) // chatPrompt accepts a list of messages and returns the prompt and images that should be used for the next chat turn. // chatPrompt truncates any messages that exceed the context window of the model, making sure to always include 1) the // latest message and 2) system messages -func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message) (prompt string, images []llm.ImageData, _ error) { +func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message, tools []api.Tool) (prompt string, images []llm.ImageData, _ error) { var system []api.Message // always include the last message n := len(msgs) - 1 @@ -29,7 +29,7 @@ func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api. } var b bytes.Buffer - if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[i:]...)}); err != nil { + if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[i:]...), Tools: tools}); err != nil { return "", nil, err } @@ -57,7 +57,7 @@ func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api. // truncate any messages that do not fit into the context window var b bytes.Buffer - if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[n:]...)}); err != nil { + if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[n:]...), Tools: tools}); err != nil { return "", nil, err } diff --git a/server/prompt_test.go b/server/prompt_test.go index d8caf3ed..02d23785 100644 --- a/server/prompt_test.go +++ b/server/prompt_test.go @@ -3,7 +3,6 @@ package server import ( "bytes" "context" - "strings" "testing" "github.com/google/go-cmp/cmp" @@ -11,14 +10,6 @@ import ( "github.com/ollama/ollama/template" ) -func tokenize(_ context.Context, s string) (tokens []int, err error) { - for range strings.Fields(s) { - tokens = append(tokens, len(tokens)) - } - - return -} - func TestChatPrompt(t *testing.T) { type expect struct { prompt string @@ -192,15 +183,11 @@ func TestChatPrompt(t *testing.T) { t.Run(tt.name, func(t *testing.T) { model := Model{Template: tmpl, ProjectorPaths: []string{"vision"}} opts := api.Options{Runner: api.Runner{NumCtx: tt.limit}} - prompt, images, err := chatPrompt(context.TODO(), &model, tokenize, &opts, tt.msgs) + prompt, images, err := chatPrompt(context.TODO(), &model, mockRunner{}.Tokenize, &opts, tt.msgs, nil) if err != nil { t.Fatal(err) } - if tt.prompt != prompt { - t.Errorf("expected %q, got %q", tt.prompt, prompt) - } - if diff := cmp.Diff(prompt, tt.prompt); diff != "" { t.Errorf("mismatch (-got +want):\n%s", diff) } diff --git a/server/routes.go b/server/routes.go index edaec691..c33b7195 100644 --- a/server/routes.go +++ b/server/routes.go @@ -9,6 +9,7 @@ import ( "fmt" "io" "log/slog" + "math" "net" "net/http" "net/netip" @@ -121,6 +122,10 @@ func (s *Server) GenerateHandler(c *gin.Context) { } caps := []Capability{CapabilityCompletion} + if req.Suffix != "" { + caps = append(caps, CapabilityInsert) + } + r, m, opts, err := s.scheduleRunner(c.Request.Context(), req.Model, caps, req.Options, req.KeepAlive) if errors.Is(err, errCapabilityCompletion) { c.JSON(http.StatusBadRequest, gin.H{"error": fmt.Sprintf("%q does not support generate", req.Model)}) @@ -149,19 +154,6 @@ func (s *Server) GenerateHandler(c *gin.Context) { prompt := req.Prompt if !req.Raw { - var msgs []api.Message - if req.System != "" { - msgs = append(msgs, api.Message{Role: "system", Content: req.System}) - } else if m.System != "" { - msgs = append(msgs, api.Message{Role: "system", Content: m.System}) - } - - for _, i := range images { - msgs = append(msgs, api.Message{Role: "user", Content: fmt.Sprintf("[img-%d]", i.ID)}) - } - - msgs = append(msgs, api.Message{Role: "user", Content: req.Prompt}) - tmpl := m.Template if req.Template != "" { tmpl, err = template.Parse(req.Template) @@ -182,7 +174,26 @@ func (s *Server) GenerateHandler(c *gin.Context) { b.WriteString(s) } - if err := tmpl.Execute(&b, template.Values{Messages: msgs}); err != nil { + var values template.Values + if req.Suffix != "" { + values.Prompt = prompt + values.Suffix = req.Suffix + } else { + var msgs []api.Message + if req.System != "" { + msgs = append(msgs, api.Message{Role: "system", Content: req.System}) + } else if m.System != "" { + msgs = append(msgs, api.Message{Role: "system", Content: m.System}) + } + + for _, i := range images { + msgs = append(msgs, api.Message{Role: "user", Content: fmt.Sprintf("[img-%d]", i.ID)}) + } + + values.Messages = append(msgs, api.Message{Role: "user", Content: req.Prompt}) + } + + if err := tmpl.Execute(&b, values); err != nil { c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()}) return } @@ -271,6 +282,121 @@ func (s *Server) GenerateHandler(c *gin.Context) { streamResponse(c, ch) } +func (s *Server) EmbedHandler(c *gin.Context) { + var req api.EmbedRequest + err := c.ShouldBindJSON(&req) + switch { + case errors.Is(err, io.EOF): + c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "missing request body"}) + return + case err != nil: + c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": err.Error()}) + return + } + + truncate := true + + if req.Truncate != nil && !*req.Truncate { + truncate = false + } + + var input []string + + switch i := req.Input.(type) { + case string: + if len(i) > 0 { + input = append(input, i) + } + case []any: + for _, v := range i { + if _, ok := v.(string); !ok { + c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "invalid input type"}) + return + } + input = append(input, v.(string)) + } + default: + c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "invalid input type"}) + return + } + + if len(input) == 0 { + c.JSON(http.StatusOK, api.EmbedResponse{Model: req.Model, Embeddings: [][]float32{}}) + return + } + + r, m, opts, err := s.scheduleRunner(c.Request.Context(), req.Model, []Capability{}, req.Options, req.KeepAlive) + if err != nil { + handleScheduleError(c, req.Model, err) + return + } + + kvData, err := getKVData(m.ModelPath, false) + if err != nil { + c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()}) + return + } + + for i, s := range input { + tokens, err := r.Tokenize(c.Request.Context(), s) + if err != nil { + c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()}) + return + } + + ctxLen := min(opts.NumCtx, int(kvData.ContextLength())) + if len(tokens) > ctxLen { + if !truncate { + c.JSON(http.StatusBadRequest, gin.H{"error": "input length exceeds maximum context length"}) + return + } + + tokens = tokens[:ctxLen] + s, err = r.Detokenize(c.Request.Context(), tokens) + if err != nil { + c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()}) + return + } + } + + input[i] = s + } + embeddings, err := r.Embed(c.Request.Context(), input) + + if err != nil { + slog.Error("embedding generation failed", "error", err) + c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to generate embedding"}) + return + } + + for i, e := range embeddings { + embeddings[i] = normalize(e) + } + + resp := api.EmbedResponse{ + Model: req.Model, + Embeddings: embeddings, + } + c.JSON(http.StatusOK, resp) +} + +func normalize(vec []float32) []float32 { + var sum float32 + for _, v := range vec { + sum += v * v + } + + norm := float32(0.0) + if sum > 0 { + norm = float32(1.0 / math.Sqrt(float64(sum))) + } + + for i := range vec { + vec[i] *= norm + } + return vec +} + func (s *Server) EmbeddingsHandler(c *gin.Context) { var req api.EmbeddingRequest if err := c.ShouldBindJSON(&req); errors.Is(err, io.EOF) { @@ -293,14 +419,24 @@ func (s *Server) EmbeddingsHandler(c *gin.Context) { return } - embedding, err := r.Embedding(c.Request.Context(), req.Prompt) + embeddings, err := r.Embed(c.Request.Context(), []string{req.Prompt}) + if err != nil { slog.Info(fmt.Sprintf("embedding generation failed: %v", err)) c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to generate embedding"}) return } - c.JSON(http.StatusOK, api.EmbeddingResponse{Embedding: embedding}) + embedding := make([]float64, len(embeddings[0])) + + for i, v := range embeddings[0] { + embedding[i] = float64(v) + } + + resp := api.EmbeddingResponse{ + Embedding: embedding, + } + c.JSON(http.StatusOK, resp) } func (s *Server) PullModelHandler(c *gin.Context) { @@ -574,13 +710,6 @@ func GetModelInfo(req api.ShowRequest) (*api.ShowResponse, error) { m.System = req.System } - if req.Template != "" { - m.Template, err = template.Parse(req.Template) - if err != nil { - return nil, err - } - } - msgs := make([]api.Message, len(m.Messages)) for i, msg := range m.Messages { msgs[i] = api.Message{Role: msg.Role, Content: msg.Content} @@ -926,6 +1055,7 @@ func (s *Server) GenerateRoutes() http.Handler { r.POST("/api/pull", s.PullModelHandler) r.POST("/api/generate", s.GenerateHandler) r.POST("/api/chat", s.ChatHandler) + r.POST("/api/embed", s.EmbedHandler) r.POST("/api/embeddings", s.EmbeddingsHandler) r.POST("/api/create", s.CreateModelHandler) r.POST("/api/push", s.PushModelHandler) @@ -939,6 +1069,7 @@ func (s *Server) GenerateRoutes() http.Handler { // Compatibility endpoints r.POST("/v1/chat/completions", openai.ChatMiddleware(), s.ChatHandler) r.POST("/v1/completions", openai.CompletionsMiddleware(), s.GenerateHandler) + r.POST("/v1/embeddings", openai.EmbeddingsMiddleware(), s.EmbedHandler) r.GET("/v1/models", openai.ListMiddleware(), s.ListModelsHandler) r.GET("/v1/models/:model", openai.RetrieveMiddleware(), s.ShowModelHandler) @@ -1159,6 +1290,10 @@ func (s *Server) ChatHandler(c *gin.Context) { } caps := []Capability{CapabilityCompletion} + if len(req.Tools) > 0 { + caps = append(caps, CapabilityTools) + } + r, m, opts, err := s.scheduleRunner(c.Request.Context(), req.Model, caps, req.Options, req.KeepAlive) if errors.Is(err, errCapabilityCompletion) { c.JSON(http.StatusBadRequest, gin.H{"error": fmt.Sprintf("%q does not support chat", req.Model)}) @@ -1181,11 +1316,11 @@ func (s *Server) ChatHandler(c *gin.Context) { return } - if req.Messages[0].Role != "system" { + if req.Messages[0].Role != "system" && m.System != "" { req.Messages = append([]api.Message{{Role: "system", Content: m.System}}, req.Messages...) } - prompt, images, err := chatPrompt(c.Request.Context(), m, r.Tokenize, opts, req.Messages) + prompt, images, err := chatPrompt(c.Request.Context(), m, r.Tokenize, opts, req.Messages, req.Tools) if err != nil { c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()}) return @@ -1228,13 +1363,13 @@ func (s *Server) ChatHandler(c *gin.Context) { }() if req.Stream != nil && !*req.Stream { - var r api.ChatResponse + var resp api.ChatResponse var sb strings.Builder for rr := range ch { switch t := rr.(type) { case api.ChatResponse: sb.WriteString(t.Message.Content) - r = t + resp = t case gin.H: msg, ok := t["error"].(string) if !ok { @@ -1249,8 +1384,16 @@ func (s *Server) ChatHandler(c *gin.Context) { } } - r.Message.Content = sb.String() - c.JSON(http.StatusOK, r) + resp.Message.Content = sb.String() + + if len(req.Tools) > 0 { + if toolCalls, ok := m.parseToolCalls(sb.String()); ok { + resp.Message.ToolCalls = toolCalls + resp.Message.Content = "" + } + } + + c.JSON(http.StatusOK, resp) return } @@ -1259,7 +1402,7 @@ func (s *Server) ChatHandler(c *gin.Context) { func handleScheduleError(c *gin.Context, name string, err error) { switch { - case errors.Is(err, errRequired): + case errors.Is(err, errCapabilities), errors.Is(err, errRequired): c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()}) case errors.Is(err, context.Canceled): c.JSON(499, gin.H{"error": "request canceled"}) diff --git a/server/routes_create_test.go b/server/routes_create_test.go index 04174b92..cb548ebd 100644 --- a/server/routes_create_test.go +++ b/server/routes_create_test.go @@ -85,6 +85,8 @@ func checkFileExists(t *testing.T, p string, expect []string) { } func TestCreateFromBin(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -111,6 +113,8 @@ func TestCreateFromBin(t *testing.T) { } func TestCreateFromModel(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -152,6 +156,8 @@ func TestCreateFromModel(t *testing.T) { } func TestCreateRemovesLayers(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -199,6 +205,8 @@ func TestCreateRemovesLayers(t *testing.T) { } func TestCreateUnsetsSystem(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -255,6 +263,8 @@ func TestCreateUnsetsSystem(t *testing.T) { } func TestCreateMergeParameters(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -358,6 +368,8 @@ func TestCreateMergeParameters(t *testing.T) { } func TestCreateReplacesMessages(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -434,6 +446,8 @@ func TestCreateReplacesMessages(t *testing.T) { } func TestCreateTemplateSystem(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -480,6 +494,8 @@ func TestCreateTemplateSystem(t *testing.T) { } func TestCreateLicenses(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -526,6 +542,8 @@ func TestCreateLicenses(t *testing.T) { } func TestCreateDetectTemplate(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() diff --git a/server/routes_delete_test.go b/server/routes_delete_test.go index 00303bd1..33a97a73 100644 --- a/server/routes_delete_test.go +++ b/server/routes_delete_test.go @@ -8,12 +8,15 @@ import ( "path/filepath" "testing" + "github.com/gin-gonic/gin" "github.com/ollama/ollama/api" "github.com/ollama/ollama/envconfig" "github.com/ollama/ollama/types/model" ) func TestDelete(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) envconfig.LoadConfig() @@ -77,6 +80,8 @@ func TestDelete(t *testing.T) { } func TestDeleteDuplicateLayers(t *testing.T) { + gin.SetMode(gin.TestMode) + p := t.TempDir() t.Setenv("OLLAMA_MODELS", p) var s Server diff --git a/server/routes_generate_test.go b/server/routes_generate_test.go new file mode 100644 index 00000000..c914b300 --- /dev/null +++ b/server/routes_generate_test.go @@ -0,0 +1,712 @@ +package server + +import ( + "bytes" + "context" + "encoding/json" + "fmt" + "io" + "net/http" + "strings" + "testing" + "time" + + "github.com/gin-gonic/gin" + "github.com/google/go-cmp/cmp" + + "github.com/ollama/ollama/api" + "github.com/ollama/ollama/gpu" + "github.com/ollama/ollama/llm" +) + +type mockRunner struct { + llm.LlamaServer + + // CompletionRequest is only valid until the next call to Completion + llm.CompletionRequest + llm.CompletionResponse +} + +func (m *mockRunner) Completion(_ context.Context, r llm.CompletionRequest, fn func(r llm.CompletionResponse)) error { + m.CompletionRequest = r + fn(m.CompletionResponse) + return nil +} + +func (mockRunner) Tokenize(_ context.Context, s string) (tokens []int, err error) { + for range strings.Fields(s) { + tokens = append(tokens, len(tokens)) + } + + return +} + +func newMockServer(mock *mockRunner) func(gpu.GpuInfoList, string, *llm.GGML, []string, []string, api.Options, int) (llm.LlamaServer, error) { + return func(gpus gpu.GpuInfoList, model string, ggml *llm.GGML, projectors, system []string, opts api.Options, numParallel int) (llm.LlamaServer, error) { + return mock, nil + } +} + +func TestGenerateChat(t *testing.T) { + gin.SetMode(gin.TestMode) + + mock := mockRunner{ + CompletionResponse: llm.CompletionResponse{ + Done: true, + DoneReason: "stop", + PromptEvalCount: 1, + PromptEvalDuration: 1, + EvalCount: 1, + EvalDuration: 1, + }, + } + + s := Server{ + sched: &Scheduler{ + pendingReqCh: make(chan *LlmRequest, 1), + finishedReqCh: make(chan *LlmRequest, 1), + expiredCh: make(chan *runnerRef, 1), + unloadedCh: make(chan any, 1), + loaded: make(map[string]*runnerRef), + newServerFn: newMockServer(&mock), + getGpuFn: gpu.GetGPUInfo, + getCpuFn: gpu.GetCPUInfo, + reschedDelay: 250 * time.Millisecond, + loadFn: func(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList, numParallel int) { + // add 10ms delay to simulate loading + time.Sleep(10 * time.Millisecond) + req.successCh <- &runnerRef{ + llama: &mock, + } + }, + }, + } + + go s.sched.Run(context.TODO()) + + w := createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "test", + Modelfile: fmt.Sprintf(`FROM %s + TEMPLATE """ +{{- if .System }}System: {{ .System }} {{ end }} +{{- if .Prompt }}User: {{ .Prompt }} {{ end }} +{{- if .Response }}Assistant: {{ .Response }} {{ end }}""" +`, createBinFile(t, llm.KV{ + "general.architecture": "llama", + "llama.block_count": uint32(1), + "llama.context_length": uint32(8192), + "llama.embedding_length": uint32(4096), + "llama.attention.head_count": uint32(32), + "llama.attention.head_count_kv": uint32(8), + "tokenizer.ggml.tokens": []string{""}, + "tokenizer.ggml.scores": []float32{0}, + "tokenizer.ggml.token_type": []int32{0}, + }, []llm.Tensor{ + {Name: "token_embd.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_norm.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_down.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_gate.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_up.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_norm.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_k.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_output.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_q.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_v.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "output.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + })), + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + t.Run("missing body", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, nil) + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"model is required"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("missing model", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{}) + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"model is required"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("missing capabilities chat", func(t *testing.T) { + w := createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "bert", + Modelfile: fmt.Sprintf("FROM %s", createBinFile(t, llm.KV{ + "general.architecture": "bert", + "bert.pooling_type": uint32(0), + }, []llm.Tensor{})), + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + w = createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "bert", + }) + + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"\"bert\" does not support chat"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("load model", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "test", + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + var actual api.ChatResponse + if err := json.NewDecoder(w.Body).Decode(&actual); err != nil { + t.Fatal(err) + } + + if actual.Model != "test" { + t.Errorf("expected model test, got %s", actual.Model) + } + + if !actual.Done { + t.Errorf("expected done true, got false") + } + + if actual.DoneReason != "load" { + t.Errorf("expected done reason load, got %s", actual.DoneReason) + } + }) + + checkChatResponse := func(t *testing.T, body io.Reader, model, content string) { + t.Helper() + + var actual api.ChatResponse + if err := json.NewDecoder(body).Decode(&actual); err != nil { + t.Fatal(err) + } + + if actual.Model != model { + t.Errorf("expected model test, got %s", actual.Model) + } + + if !actual.Done { + t.Errorf("expected done false, got true") + } + + if actual.DoneReason != "stop" { + t.Errorf("expected done reason stop, got %s", actual.DoneReason) + } + + if diff := cmp.Diff(actual.Message, api.Message{ + Role: "assistant", + Content: content, + }); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + if actual.PromptEvalCount == 0 { + t.Errorf("expected prompt eval count > 0, got 0") + } + + if actual.PromptEvalDuration == 0 { + t.Errorf("expected prompt eval duration > 0, got 0") + } + + if actual.EvalCount == 0 { + t.Errorf("expected eval count > 0, got 0") + } + + if actual.EvalDuration == 0 { + t.Errorf("expected eval duration > 0, got 0") + } + + if actual.LoadDuration == 0 { + t.Errorf("expected load duration > 0, got 0") + } + + if actual.TotalDuration == 0 { + t.Errorf("expected total duration > 0, got 0") + } + } + + mock.CompletionResponse.Content = "Hi!" + t.Run("messages", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "test", + Messages: []api.Message{ + {Role: "user", Content: "Hello!"}, + }, + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkChatResponse(t, w.Body, "test", "Hi!") + }) + + w = createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "test-system", + Modelfile: "FROM test\nSYSTEM You are a helpful assistant.", + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + t.Run("messages with model system", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "test-system", + Messages: []api.Message{ + {Role: "user", Content: "Hello!"}, + }, + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "System: You are a helpful assistant. User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkChatResponse(t, w.Body, "test-system", "Hi!") + }) + + mock.CompletionResponse.Content = "Abra kadabra!" + t.Run("messages with system", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "test-system", + Messages: []api.Message{ + {Role: "system", Content: "You can perform magic tricks."}, + {Role: "user", Content: "Hello!"}, + }, + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "System: You can perform magic tricks. User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkChatResponse(t, w.Body, "test-system", "Abra kadabra!") + }) + + t.Run("messages with interleaved system", func(t *testing.T) { + w := createRequest(t, s.ChatHandler, api.ChatRequest{ + Model: "test-system", + Messages: []api.Message{ + {Role: "user", Content: "Hello!"}, + {Role: "assistant", Content: "I can help you with that."}, + {Role: "system", Content: "You can perform magic tricks."}, + {Role: "user", Content: "Help me write tests."}, + }, + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "System: You are a helpful assistant. User: Hello! Assistant: I can help you with that. System: You can perform magic tricks. User: Help me write tests. "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkChatResponse(t, w.Body, "test-system", "Abra kadabra!") + }) +} + +func TestGenerate(t *testing.T) { + gin.SetMode(gin.TestMode) + + mock := mockRunner{ + CompletionResponse: llm.CompletionResponse{ + Done: true, + DoneReason: "stop", + PromptEvalCount: 1, + PromptEvalDuration: 1, + EvalCount: 1, + EvalDuration: 1, + }, + } + + s := Server{ + sched: &Scheduler{ + pendingReqCh: make(chan *LlmRequest, 1), + finishedReqCh: make(chan *LlmRequest, 1), + expiredCh: make(chan *runnerRef, 1), + unloadedCh: make(chan any, 1), + loaded: make(map[string]*runnerRef), + newServerFn: newMockServer(&mock), + getGpuFn: gpu.GetGPUInfo, + getCpuFn: gpu.GetCPUInfo, + reschedDelay: 250 * time.Millisecond, + loadFn: func(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList, numParallel int) { + req.successCh <- &runnerRef{ + llama: &mock, + } + }, + }, + } + + go s.sched.Run(context.TODO()) + + w := createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "test", + Modelfile: fmt.Sprintf(`FROM %s + TEMPLATE """ +{{- if .System }}System: {{ .System }} {{ end }} +{{- if .Prompt }}User: {{ .Prompt }} {{ end }} +{{- if .Response }}Assistant: {{ .Response }} {{ end }}""" +`, createBinFile(t, llm.KV{ + "general.architecture": "llama", + "llama.block_count": uint32(1), + "llama.context_length": uint32(8192), + "llama.embedding_length": uint32(4096), + "llama.attention.head_count": uint32(32), + "llama.attention.head_count_kv": uint32(8), + "tokenizer.ggml.tokens": []string{""}, + "tokenizer.ggml.scores": []float32{0}, + "tokenizer.ggml.token_type": []int32{0}, + }, []llm.Tensor{ + {Name: "token_embd.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_norm.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_down.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_gate.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_up.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.ffn_norm.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_k.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_output.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_q.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "blk.0.attn_v.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + {Name: "output.weight", Shape: []uint64{1}, WriterTo: bytes.NewReader(make([]byte, 4))}, + })), + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + t.Run("missing body", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, nil) + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"model is required"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("missing model", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{}) + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"model is required"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("missing capabilities generate", func(t *testing.T) { + w := createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "bert", + Modelfile: fmt.Sprintf("FROM %s", createBinFile(t, llm.KV{ + "general.architecture": "bert", + "bert.pooling_type": uint32(0), + }, []llm.Tensor{})), + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + w = createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "bert", + }) + + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"\"bert\" does not support generate"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("missing capabilities suffix", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test", + Prompt: "def add(", + Suffix: " return c", + }) + + if w.Code != http.StatusBadRequest { + t.Errorf("expected status 400, got %d", w.Code) + } + + if diff := cmp.Diff(w.Body.String(), `{"error":"test does not support insert"}`); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + }) + + t.Run("load model", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test", + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + var actual api.GenerateResponse + if err := json.NewDecoder(w.Body).Decode(&actual); err != nil { + t.Fatal(err) + } + + if actual.Model != "test" { + t.Errorf("expected model test, got %s", actual.Model) + } + + if !actual.Done { + t.Errorf("expected done true, got false") + } + + if actual.DoneReason != "load" { + t.Errorf("expected done reason load, got %s", actual.DoneReason) + } + }) + + checkGenerateResponse := func(t *testing.T, body io.Reader, model, content string) { + t.Helper() + + var actual api.GenerateResponse + if err := json.NewDecoder(body).Decode(&actual); err != nil { + t.Fatal(err) + } + + if actual.Model != model { + t.Errorf("expected model test, got %s", actual.Model) + } + + if !actual.Done { + t.Errorf("expected done false, got true") + } + + if actual.DoneReason != "stop" { + t.Errorf("expected done reason stop, got %s", actual.DoneReason) + } + + if actual.Response != content { + t.Errorf("expected response %s, got %s", content, actual.Response) + } + + if actual.Context == nil { + t.Errorf("expected context not nil") + } + + if actual.PromptEvalCount == 0 { + t.Errorf("expected prompt eval count > 0, got 0") + } + + if actual.PromptEvalDuration == 0 { + t.Errorf("expected prompt eval duration > 0, got 0") + } + + if actual.EvalCount == 0 { + t.Errorf("expected eval count > 0, got 0") + } + + if actual.EvalDuration == 0 { + t.Errorf("expected eval duration > 0, got 0") + } + + if actual.LoadDuration == 0 { + t.Errorf("expected load duration > 0, got 0") + } + + if actual.TotalDuration == 0 { + t.Errorf("expected total duration > 0, got 0") + } + } + + mock.CompletionResponse.Content = "Hi!" + t.Run("prompt", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test", + Prompt: "Hello!", + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkGenerateResponse(t, w.Body, "test", "Hi!") + }) + + w = createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "test-system", + Modelfile: "FROM test\nSYSTEM You are a helpful assistant.", + }) + + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d", w.Code) + } + + t.Run("prompt with model system", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test-system", + Prompt: "Hello!", + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "System: You are a helpful assistant. User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkGenerateResponse(t, w.Body, "test-system", "Hi!") + }) + + mock.CompletionResponse.Content = "Abra kadabra!" + t.Run("prompt with system", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test-system", + Prompt: "Hello!", + System: "You can perform magic tricks.", + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "System: You can perform magic tricks. User: Hello! "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkGenerateResponse(t, w.Body, "test-system", "Abra kadabra!") + }) + + t.Run("prompt with template", func(t *testing.T) { + w := createRequest(t, s.GenerateHandler, api.GenerateRequest{ + Model: "test-system", + Prompt: "Help me write tests.", + System: "You can perform magic tricks.", + Template: `{{- if .System }}{{ .System }} {{ end }} +{{- if .Prompt }}### USER {{ .Prompt }} {{ end }} +{{- if .Response }}### ASSISTANT {{ .Response }} {{ end }}`, + Stream: &stream, + }) + + if w.Code != http.StatusOK { + t.Errorf("expected status 200, got %d", w.Code) + } + + if diff := cmp.Diff(mock.CompletionRequest.Prompt, "You can perform magic tricks. ### USER Help me write tests. "); diff != "" { + t.Errorf("mismatch (-got +want):\n%s", diff) + } + + checkGenerateResponse(t, w.Body, "test-system", "Abra kadabra!") + }) + + w = createRequest(t, s.CreateModelHandler, api.CreateRequest{ + Model: "test-suffix", + Modelfile: `FROM test +TEMPLATE """{{- if .Suffix }}
 {{ .Prompt }} {{ .Suffix }} 
+{{- else }}{{ .Prompt }}
+{{- end }}"""`,
+	})
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("expected status 200, got %d", w.Code)
+	}
+
+	t.Run("prompt with suffix", func(t *testing.T) {
+		w := createRequest(t, s.GenerateHandler, api.GenerateRequest{
+			Model:  "test-suffix",
+			Prompt: "def add(",
+			Suffix: "    return c",
+		})
+
+		if w.Code != http.StatusOK {
+			t.Errorf("expected status 200, got %d", w.Code)
+		}
+
+		if diff := cmp.Diff(mock.CompletionRequest.Prompt, "
 def add(     return c "); diff != "" {
+			t.Errorf("mismatch (-got +want):\n%s", diff)
+		}
+	})
+
+	t.Run("prompt without suffix", func(t *testing.T) {
+		w := createRequest(t, s.GenerateHandler, api.GenerateRequest{
+			Model:  "test-suffix",
+			Prompt: "def add(",
+		})
+
+		if w.Code != http.StatusOK {
+			t.Errorf("expected status 200, got %d", w.Code)
+		}
+
+		if diff := cmp.Diff(mock.CompletionRequest.Prompt, "def add("); diff != "" {
+			t.Errorf("mismatch (-got +want):\n%s", diff)
+		}
+	})
+
+	t.Run("raw", func(t *testing.T) {
+		w := createRequest(t, s.GenerateHandler, api.GenerateRequest{
+			Model:  "test-system",
+			Prompt: "Help me write tests.",
+			Raw:    true,
+			Stream: &stream,
+		})
+
+		if w.Code != http.StatusOK {
+			t.Errorf("expected status 200, got %d", w.Code)
+		}
+
+		if diff := cmp.Diff(mock.CompletionRequest.Prompt, "Help me write tests."); diff != "" {
+			t.Errorf("mismatch (-got +want):\n%s", diff)
+		}
+	})
+}
diff --git a/server/routes_list_test.go b/server/routes_list_test.go
index d04be9d6..c2d9c113 100644
--- a/server/routes_list_test.go
+++ b/server/routes_list_test.go
@@ -7,11 +7,14 @@ import (
 	"slices"
 	"testing"
 
+	"github.com/gin-gonic/gin"
 	"github.com/ollama/ollama/api"
 	"github.com/ollama/ollama/envconfig"
 )
 
 func TestList(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
 	t.Setenv("OLLAMA_MODELS", t.TempDir())
 	envconfig.LoadConfig()
 
diff --git a/server/routes_test.go b/server/routes_test.go
index 50eaf7e9..97786ba2 100644
--- a/server/routes_test.go
+++ b/server/routes_test.go
@@ -7,6 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -272,6 +273,77 @@ func Test_Routes(t *testing.T) {
 				assert.Equal(t, "library", retrieveResp.OwnedBy)
 			},
 		},
+		{
+			Name:   "Embed Handler Empty Input",
+			Method: http.MethodPost,
+			Path:   "/api/embed",
+			Setup: func(t *testing.T, req *http.Request) {
+				embedReq := api.EmbedRequest{
+					Model: "t-bone",
+					Input: "",
+				}
+				jsonData, err := json.Marshal(embedReq)
+				require.NoError(t, err)
+				req.Body = io.NopCloser(bytes.NewReader(jsonData))
+			},
+			Expected: func(t *testing.T, resp *http.Response) {
+				contentType := resp.Header.Get("Content-Type")
+				if contentType != "application/json; charset=utf-8" {
+					t.Fatalf("expected content type application/json; charset=utf-8, got %s", contentType)
+				}
+				body, err := io.ReadAll(resp.Body)
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				var embedResp api.EmbedResponse
+				err = json.Unmarshal(body, &embedResp)
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				if embedResp.Model != "t-bone" {
+					t.Fatalf("expected model t-bone, got %s", embedResp.Model)
+				}
+
+				if embedResp.Embeddings == nil {
+					t.Fatalf("expected embeddings to not be nil, got %v", embedResp.Embeddings)
+				}
+
+				if len(embedResp.Embeddings) != 0 {
+					t.Fatalf("expected embeddings to be empty, got %v", embedResp.Embeddings)
+				}
+			},
+		},
+		{
+			Name:   "Embed Handler Invalid Input",
+			Method: http.MethodPost,
+			Path:   "/api/embed",
+			Setup: func(t *testing.T, req *http.Request) {
+				embedReq := api.EmbedRequest{
+					Model: "t-bone",
+					Input: 2,
+				}
+				jsonData, err := json.Marshal(embedReq)
+				require.NoError(t, err)
+				req.Body = io.NopCloser(bytes.NewReader(jsonData))
+			},
+			Expected: func(t *testing.T, resp *http.Response) {
+				contentType := resp.Header.Get("Content-Type")
+				if contentType != "application/json; charset=utf-8" {
+					t.Fatalf("expected content type application/json; charset=utf-8, got %s", contentType)
+				}
+				_, err := io.ReadAll(resp.Body)
+
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				if resp.StatusCode != http.StatusBadRequest {
+					t.Fatalf("expected status code 400, got %d", resp.StatusCode)
+				}
+			},
+		},
 	}
 
 	t.Setenv("OLLAMA_MODELS", t.TempDir())
@@ -420,3 +492,38 @@ func TestShow(t *testing.T) {
 		t.Fatal("Expected projector architecture to be 'clip', but got", resp.ProjectorInfo["general.architecture"])
 	}
 }
+
+func TestNormalize(t *testing.T) {
+	type testCase struct {
+		input []float32
+	}
+
+	testCases := []testCase{
+		{input: []float32{1}},
+		{input: []float32{0, 1, 2, 3}},
+		{input: []float32{0.1, 0.2, 0.3}},
+		{input: []float32{-0.1, 0.2, 0.3, -0.4}},
+		{input: []float32{0, 0, 0}},
+	}
+
+	isNormalized := func(vec []float32) (res bool) {
+		sum := 0.0
+		for _, v := range vec {
+			sum += float64(v * v)
+		}
+		if math.Abs(sum-1) > 1e-6 {
+			return sum == 0
+		} else {
+			return true
+		}
+	}
+
+	for _, tc := range testCases {
+		t.Run("", func(t *testing.T) {
+			normalized := normalize(tc.input)
+			if !isNormalized(normalized) {
+				t.Errorf("Vector %v is not normalized", tc.input)
+			}
+		})
+	}
+}
diff --git a/server/sched_test.go b/server/sched_test.go
index 3fbd188a..4b000331 100644
--- a/server/sched_test.go
+++ b/server/sched_test.go
@@ -642,8 +642,8 @@ type mockLlm struct {
 	pingResp           error
 	waitResp           error
 	completionResp     error
-	embeddingResp      []float64
-	embeddingRespErr   error
+	embedResp          [][]float32
+	embedRespErr       error
 	tokenizeResp       []int
 	tokenizeRespErr    error
 	detokenizeResp     string
@@ -660,8 +660,8 @@ func (s *mockLlm) WaitUntilRunning(ctx context.Context) error { return s.waitRes
 func (s *mockLlm) Completion(ctx context.Context, req llm.CompletionRequest, fn func(llm.CompletionResponse)) error {
 	return s.completionResp
 }
-func (s *mockLlm) Embedding(ctx context.Context, prompt string) ([]float64, error) {
-	return s.embeddingResp, s.embeddingRespErr
+func (s *mockLlm) Embed(ctx context.Context, input []string) ([][]float32, error) {
+	return s.embedResp, s.embedRespErr
 }
 func (s *mockLlm) Tokenize(ctx context.Context, content string) ([]int, error) {
 	return s.tokenizeResp, s.tokenizeRespErr
diff --git a/server/testdata/tools/command-r-plus.gotmpl b/server/testdata/tools/command-r-plus.gotmpl
new file mode 100644
index 00000000..f30124e3
--- /dev/null
+++ b/server/testdata/tools/command-r-plus.gotmpl
@@ -0,0 +1,67 @@
+{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>
+{{- if .Tools }}# Safety Preamble
+The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
+
+# System Preamble
+## Basic Rules
+You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
+
+{{ if .System }}# User Preamble
+{{ .System }}
+{{- end }}
+
+## Available Tools
+Here is a list of tools that you have available to you:
+{{- range .Tools }}
+
+```python
+def {{ .Function.Name }}(
+{{- range $name, $property := .Function.Parameters.Properties }}{{ $name }}: {{ $property.Type }}, {{ end }}) -> List[Dict]:
+    """{{ .Function.Description }}
+
+{{- if .Function.Parameters.Properties }}
+
+    Args:
+{{- range $name, $property := .Function.Parameters.Properties }}
+        {{ $name }} ({{ $property.Type }}): {{ $property.Description }}
+{{- end }}
+{{- end }}
+    """
+    pass
+```
+{{- end }}
+{{- else if .System }}{{ .System }}
+{{- end }}<|END_OF_TURN_TOKEN|>
+{{- end }}
+{{- range .Messages }}
+{{- if eq .Role "system" }}
+{{- continue }}
+{{- end }}<|START_OF_TURN_TOKEN|>
+{{- if eq .Role "user" }}<|USER_TOKEN|>{{ .Content }}
+{{- else if eq .Role "assistant" }}<|CHATBOT_TOKEN|>
+{{- if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}
+Action: ```json
+[
+{{- range .ToolCalls }}
+    {
+        "tool_name": "{{ .Function.Name }}",
+        "parameters": {{ .Function.Arguments }}
+    }
+{{- end }}
+]```
+{{ continue }}
+{{ end }}
+{{- else if eq .Role "tool" }}<|SYSTEM_TOKEN|>
+{{ .Content }}
+{{- end }}<|END_OF_TURN_TOKEN|>
+{{- end }}
+{{- if .Tools }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:
+```json
+[
+    {
+        "tool_name": title of the tool in the specification,
+        "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters
+    }
+]```
+{{- end }}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
\ No newline at end of file
diff --git a/server/testdata/tools/command-r-plus.out b/server/testdata/tools/command-r-plus.out
new file mode 100644
index 00000000..425af75a
--- /dev/null
+++ b/server/testdata/tools/command-r-plus.out
@@ -0,0 +1,39 @@
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
+The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
+
+# System Preamble
+## Basic Rules
+You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
+
+# User Preamble
+You are a knowledgable assistant. You can answer questions and perform tasks.
+
+## Available Tools
+Here is a list of tools that you have available to you:
+
+```python
+def get_current_weather(format: string, location: string, ) -> List[Dict]:
+    """Get the current weather
+
+    Args:
+        format (string): The temperature unit to use. Infer this from the users location.
+        location (string): The city and state, e.g. San Francisco, CA
+    """
+    pass
+```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>What's the weather like today in Paris?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+Action: ```json
+[
+    {
+        "tool_name": "get_current_weather",
+        "parameters": {"format":"celsius","location":"Paris, France"}
+    }
+]```
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>
+22<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>The current temperature in Paris, France is 22 degrees Celsius.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>What's the weather like today in San Francisco and Toronto?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:
+```json
+[
+    {
+        "tool_name": title of the tool in the specification,
+        "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters
+    }
+]```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
\ No newline at end of file
diff --git a/server/testdata/tools/firefunction.gotmpl b/server/testdata/tools/firefunction.gotmpl
new file mode 100644
index 00000000..312be205
--- /dev/null
+++ b/server/testdata/tools/firefunction.gotmpl
@@ -0,0 +1,31 @@
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+{{- if .System }}
+{{ .System }}
+{{- end }}
+In addition to plain text responses, you can chose to call one or more of the provided functions.
+
+Use the following rule to decide when to call a function:
+  * if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so
+  * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls
+
+If you decide to call functions:
+  * prefix function calls with functools marker (no closing marker required)
+  * all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...]
+  * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples
+  * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0
+  * make sure you pick the right functions that match the user intent
+
+Available functions as JSON spec:
+{{- if .Tools }}
+{{ .Tools }}
+{{- end }}<|eot_id|>
+{{- end }}
+{{- range .Messages }}<|start_header_id|>
+{{- if or (eq .Role "user") (eq .Role "assistant") (eq .Role "tool") }}{{ .Role }}
+{{- end }}<|end_header_id|>
+{{- if .Content }}{{ .Content }}
+{{- else if .ToolCalls }} functools[
+{{- range .ToolCalls }}{{ "{" }}"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}{{ "}" }}
+{{- end }}]
+{{- end }}<|eot_id|>
+{{- end }}<|start_header_id|>assistant<|end_header_id|>
\ No newline at end of file
diff --git a/server/testdata/tools/firefunction.out b/server/testdata/tools/firefunction.out
new file mode 100644
index 00000000..be50175e
--- /dev/null
+++ b/server/testdata/tools/firefunction.out
@@ -0,0 +1,17 @@
+<|start_header_id|>system<|end_header_id|>
+You are a knowledgable assistant. You can answer questions and perform tasks.
+In addition to plain text responses, you can chose to call one or more of the provided functions.
+
+Use the following rule to decide when to call a function:
+  * if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so
+  * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls
+
+If you decide to call functions:
+  * prefix function calls with functools marker (no closing marker required)
+  * all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...]
+  * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples
+  * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0
+  * make sure you pick the right functions that match the user intent
+
+Available functions as JSON spec:
+[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}]<|eot_id|><|start_header_id|><|end_header_id|>You are a knowledgable assistant. You can answer questions and perform tasks.<|eot_id|><|start_header_id|>user<|end_header_id|>What's the weather like today in Paris?<|eot_id|><|start_header_id|>assistant<|end_header_id|> functools[{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}]<|eot_id|><|start_header_id|>tool<|end_header_id|>22<|eot_id|><|start_header_id|>assistant<|end_header_id|>The current temperature in Paris, France is 22 degrees Celsius.<|eot_id|><|start_header_id|>user<|end_header_id|>What's the weather like today in San Francisco and Toronto?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
\ No newline at end of file
diff --git a/server/testdata/tools/llama3-groq-tool-use.gotmpl b/server/testdata/tools/llama3-groq-tool-use.gotmpl
new file mode 100644
index 00000000..45e9b462
--- /dev/null
+++ b/server/testdata/tools/llama3-groq-tool-use.gotmpl
@@ -0,0 +1,43 @@
+{{- if .Messages }}
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}
+{{- if .Tools }} You are provided with function signatures within  XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within  XML tags as follows:
+
+{"name": ,"arguments": }
+
+
+Here are the available tools:
+
+{{- range .Tools }} {{ .Function }}
+{{- end }} 
+{{- end }}
+{{- end }}<|eot_id|>
+{{- range .Messages }}
+{{- if ne .Role "system" }}<|start_header_id|>{{ .Role }}<|end_header_id|>
+
+{{ if eq .Role "user" }}{{ .Content }}
+{{- else if eq .Role "assistant" }}
+{{- if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}
+{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{- end }}
+
+{{- end }}
+{{- else if eq .Role "tool" }}
+{{ .Content }}
+
+{{- end }}<|eot_id|>
+{{- end }}
+{{- end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ else }}
+{{ if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}{{ .Response }}
+{{- if .Response }}<|eot_id|>
+{{- end }}
\ No newline at end of file
diff --git a/server/testdata/tools/llama3-groq-tool-use.out b/server/testdata/tools/llama3-groq-tool-use.out
new file mode 100644
index 00000000..75a49558
--- /dev/null
+++ b/server/testdata/tools/llama3-groq-tool-use.out
@@ -0,0 +1,24 @@
+<|start_header_id|>system<|end_header_id|>
+
+You are a knowledgable assistant. You can answer questions and perform tasks. You are provided with function signatures within  XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within  XML tags as follows:
+
+{"name": ,"arguments": }
+
+
+Here are the available tools:
+ {"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}} <|eot_id|><|start_header_id|>user<|end_header_id|>
+
+What's the weather like today in Paris?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+
+{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}
+<|eot_id|><|start_header_id|>tool<|end_header_id|>
+
+
+22
+<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+The current temperature in Paris, France is 22 degrees Celsius.<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+What's the weather like today in San Francisco and Toronto?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
diff --git a/server/testdata/tools/messages.json b/server/testdata/tools/messages.json
new file mode 100644
index 00000000..1a3d1f56
--- /dev/null
+++ b/server/testdata/tools/messages.json
@@ -0,0 +1,39 @@
+[
+  {
+    "role": "system",
+    "content": "You are a knowledgable assistant. You can answer questions and perform tasks."
+  },
+  {
+    "role": "user",
+    "content": "What's the weather like today in Paris?"
+  },
+  {
+    "role": "assistant",
+    "tool_calls": [
+      {
+        "id": "89a1e453-0bce-4de3-a456-c54bed09c520",
+        "type": "function",
+        "function": {
+          "name": "get_current_weather",
+          "arguments": {
+            "location": "Paris, France",
+            "format": "celsius"
+          }
+        }
+      }
+    ]
+  },
+  {
+    "role": "tool",
+    "tool_call_id": "89a1e453-0bce-4de3-a456-c54bed09c520",
+    "content": "22"
+  },
+  {
+    "role": "assistant",
+    "content": "The current temperature in Paris, France is 22 degrees Celsius."
+  },
+  {
+    "role": "user",
+    "content": "What's the weather like today in San Francisco and Toronto?"
+  }
+]
diff --git a/server/testdata/tools/mistral.gotmpl b/server/testdata/tools/mistral.gotmpl
new file mode 100644
index 00000000..b08d6c2c
--- /dev/null
+++ b/server/testdata/tools/mistral.gotmpl
@@ -0,0 +1,15 @@
+{{- range $index, $_ := .Messages }}
+{{- if eq .Role "user" }}
+{{- if and (eq (len (slice $.Messages $index)) 1) $.Tools }}[AVAILABLE_TOOLS] {{ $.Tools }}[/AVAILABLE_TOOLS]
+{{- end }}[INST] {{ if and (eq (len (slice $.Messages $index)) 1) $.System }}{{ $.System }}
+
+{{ end }}{{ .Content }}[/INST]
+{{- else if eq .Role "assistant" }}
+{{- if .Content }} {{ .Content }}
+{{- else if .ToolCalls }}[TOOL_CALLS] [
+{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{- end }}]
+{{- end }}
+{{- else if eq .Role "tool" }}[TOOL_RESULTS] {"content": {{ .Content }}}[/TOOL_RESULTS]
+{{- end }}
+{{- end }}
\ No newline at end of file
diff --git a/server/testdata/tools/mistral.out b/server/testdata/tools/mistral.out
new file mode 100644
index 00000000..31d8cdd6
--- /dev/null
+++ b/server/testdata/tools/mistral.out
@@ -0,0 +1,3 @@
+[INST] What's the weather like today in Paris?[/INST][TOOL_CALLS] [{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}][TOOL_RESULTS] {"content": 22}[/TOOL_RESULTS] The current temperature in Paris, France is 22 degrees Celsius.[AVAILABLE_TOOLS] [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}][/AVAILABLE_TOOLS][INST] You are a knowledgable assistant. You can answer questions and perform tasks.
+
+What's the weather like today in San Francisco and Toronto?[/INST]
\ No newline at end of file
diff --git a/server/testdata/tools/tools.json b/server/testdata/tools/tools.json
new file mode 100644
index 00000000..17260bf8
--- /dev/null
+++ b/server/testdata/tools/tools.json
@@ -0,0 +1,30 @@
+[
+  {
+    "type": "function",
+    "function": {
+      "name": "get_current_weather",
+      "description": "Get the current weather",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "location": {
+            "type": "string",
+            "description": "The city and state, e.g. San Francisco, CA"
+          },
+          "format": {
+            "type": "string",
+            "enum": [
+              "celsius",
+              "fahrenheit"
+            ],
+            "description": "The temperature unit to use. Infer this from the users location."
+          }
+        },
+        "required": [
+          "location",
+          "format"
+        ]
+      }
+    }
+  }
+]
diff --git a/template/template.go b/template/template.go
index 90014ec1..b5bfb16c 100644
--- a/template/template.go
+++ b/template/template.go
@@ -102,8 +102,15 @@ var response = parse.ActionNode{
 	},
 }
 
+var funcs = template.FuncMap{
+	"json": func(v any) string {
+		b, _ := json.Marshal(v)
+		return string(b)
+	},
+}
+
 func Parse(s string) (*Template, error) {
-	tmpl := template.New("").Option("missingkey=zero")
+	tmpl := template.New("").Option("missingkey=zero").Funcs(funcs)
 
 	tmpl, err := tmpl.Parse(s)
 	if err != nil {
@@ -127,7 +134,7 @@ func (t *Template) Vars() []string {
 	var vars []string
 	for _, tt := range t.Templates() {
 		for _, n := range tt.Root.Nodes {
-			vars = append(vars, parseNode(n)...)
+			vars = append(vars, Identifiers(n)...)
 		}
 	}
 
@@ -143,17 +150,74 @@ func (t *Template) Vars() []string {
 
 type Values struct {
 	Messages []api.Message
+	api.Tools
+	Prompt string
+	Suffix string
 
 	// forceLegacy is a flag used to test compatibility with legacy templates
 	forceLegacy bool
 }
 
+func (t *Template) Subtree(fn func(parse.Node) bool) *template.Template {
+	var walk func(parse.Node) parse.Node
+	walk = func(n parse.Node) parse.Node {
+		if fn(n) {
+			return n
+		}
+
+		switch t := n.(type) {
+		case *parse.ListNode:
+			for _, c := range t.Nodes {
+				if n := walk(c); n != nil {
+					return n
+				}
+			}
+		case *parse.BranchNode:
+			for _, n := range []*parse.ListNode{t.List, t.ElseList} {
+				if n != nil {
+					if n := walk(n); n != nil {
+						return n
+					}
+				}
+			}
+		case *parse.IfNode:
+			return walk(&t.BranchNode)
+		case *parse.WithNode:
+			return walk(&t.BranchNode)
+		case *parse.RangeNode:
+			return walk(&t.BranchNode)
+		}
+
+		return nil
+	}
+
+	if n := walk(t.Tree.Root); n != nil {
+		return (&template.Template{
+			Tree: &parse.Tree{
+				Root: &parse.ListNode{
+					Nodes: []parse.Node{n},
+				},
+			},
+		}).Funcs(funcs)
+	}
+
+	return nil
+}
+
 func (t *Template) Execute(w io.Writer, v Values) error {
 	system, messages := collate(v.Messages)
-	if !v.forceLegacy && slices.Contains(t.Vars(), "messages") {
+	if v.Prompt != "" && v.Suffix != "" {
+		return t.Template.Execute(w, map[string]any{
+			"Prompt":   v.Prompt,
+			"Suffix":   v.Suffix,
+			"Response": "",
+		})
+	} else if !v.forceLegacy && slices.Contains(t.Vars(), "messages") {
 		return t.Template.Execute(w, map[string]any{
 			"System":   system,
 			"Messages": messages,
+			"Tools":    v.Tools,
+			"Response": "",
 		})
 	}
 
@@ -161,7 +225,7 @@ func (t *Template) Execute(w io.Writer, v Values) error {
 	var b bytes.Buffer
 	var prompt, response string
 	for _, m := range messages {
-		execute := func () error {
+		execute := func() error {
 			if err := t.Template.Execute(&b, map[string]any{
 				"System":   system,
 				"Prompt":   prompt,
@@ -198,12 +262,8 @@ func (t *Template) Execute(w io.Writer, v Values) error {
 
 	var cut bool
 	nodes := deleteNode(t.Template.Root.Copy(), func(n parse.Node) bool {
-		switch t := n.(type) {
-		case *parse.ActionNode:
-		case *parse.FieldNode:
-			if slices.Contains(t.Ident, "Response") {
-				cut = true
-			}
+		if field, ok := n.(*parse.FieldNode); ok && slices.Contains(field.Ident, "Response") {
+			cut = true
 		}
 
 		return cut
@@ -211,8 +271,9 @@ func (t *Template) Execute(w io.Writer, v Values) error {
 
 	tree := parse.Tree{Root: nodes.(*parse.ListNode)}
 	if err := template.Must(template.New("").AddParseTree("", &tree)).Execute(&b, map[string]any{
-		"System": system,
-		"Prompt": prompt,
+		"System":   system,
+		"Prompt":   prompt,
+		"Response": "",
 	}); err != nil {
 		return err
 	}
@@ -255,50 +316,46 @@ func collate(msgs []api.Message) (string, []*api.Message) {
 	return strings.Join(system, "\n\n"), collated
 }
 
-func parseNode(n parse.Node) []string {
+// Identifiers walks the node tree returning any identifiers it finds along the way
+func Identifiers(n parse.Node) []string {
 	switch n := n.(type) {
+	case *parse.ListNode:
+		var names []string
+		for _, n := range n.Nodes {
+			names = append(names, Identifiers(n)...)
+		}
+
+		return names
+	case *parse.TemplateNode:
+		return Identifiers(n.Pipe)
 	case *parse.ActionNode:
-		return parseNode(n.Pipe)
+		return Identifiers(n.Pipe)
+	case *parse.BranchNode:
+		names := Identifiers(n.Pipe)
+		for _, n := range []*parse.ListNode{n.List, n.ElseList} {
+			if n != nil {
+				names = append(names, Identifiers(n)...)
+			}
+		}
+		return names
 	case *parse.IfNode:
-		names := parseNode(n.Pipe)
-		names = append(names, parseNode(n.List)...)
-		if n.ElseList != nil {
-			names = append(names, parseNode(n.ElseList)...)
-		}
-		return names
+		return Identifiers(&n.BranchNode)
 	case *parse.RangeNode:
-		names := parseNode(n.Pipe)
-		names = append(names, parseNode(n.List)...)
-		if n.ElseList != nil {
-			names = append(names, parseNode(n.ElseList)...)
-		}
-		return names
+		return Identifiers(&n.BranchNode)
 	case *parse.WithNode:
-		names := parseNode(n.Pipe)
-		names = append(names, parseNode(n.List)...)
-		if n.ElseList != nil {
-			names = append(names, parseNode(n.ElseList)...)
-		}
-		return names
+		return Identifiers(&n.BranchNode)
 	case *parse.PipeNode:
 		var names []string
 		for _, c := range n.Cmds {
 			for _, a := range c.Args {
-				names = append(names, parseNode(a)...)
+				names = append(names, Identifiers(a)...)
 			}
 		}
-		return names
-	case *parse.ListNode:
-		var names []string
-		for _, n := range n.Nodes {
-			names = append(names, parseNode(n)...)
-		}
-
 		return names
 	case *parse.FieldNode:
 		return n.Ident
-	case *parse.TemplateNode:
-		return parseNode(n.Pipe)
+	case *parse.VariableNode:
+		return n.Ident
 	}
 
 	return nil
diff --git a/template/template_test.go b/template/template_test.go
index c678f1b1..ae0db80b 100644
--- a/template/template_test.go
+++ b/template/template_test.go
@@ -359,3 +359,38 @@ Answer: `,
 		})
 	}
 }
+
+func TestExecuteWithSuffix(t *testing.T) {
+	tmpl, err := Parse(`{{- if .Suffix }}
 {{ .Prompt }} {{ .Suffix }} 
+{{- else }}{{ .Prompt }}
+{{- end }}`)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	cases := []struct {
+		name   string
+		values Values
+		expect string
+	}{
+		{
+			"message", Values{Messages: []api.Message{{Role: "user", Content: "hello"}}}, "hello",
+		},
+		{
+			"prompt suffix", Values{Prompt: "def add(", Suffix: "return x"}, "
 def add( return x ",
+		},
+	}
+
+	for _, tt := range cases {
+		t.Run(tt.name, func(t *testing.T) {
+			var b bytes.Buffer
+			if err := tmpl.Execute(&b, tt.values); err != nil {
+				t.Fatal(err)
+			}
+
+			if diff := cmp.Diff(b.String(), tt.expect); diff != "" {
+				t.Errorf("mismatch (-got +want):\n%s", diff)
+			}
+		})
+	}
+}