wip go engine

Co-authored-by: Patrick Devine <pdevine@sonic.net>

README.md

 # Ollama
 
-Ollama is a tool for running large language models. It's designed to be easy to use and fast.
+A fast runtime for large language models, powered by [llama.cpp](https://github.com/ggerganov/llama.cpp).
 
 > _Note: this project is a work in progress. Certain models that can be run with `ollama` are intended for research and/or non-commercial use only._
 

api/client.go

+package api
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+
+	"github.com/ollama/ollama/signature"
+)
+
+type Client struct {
+	Name       string
+	Version    string
+	URL        string
+	HTTP       http.Client
+	Headers    http.Header
+	PrivateKey []byte
+}
+
+func checkError(resp *http.Response, body []byte) error {
+	if resp.StatusCode >= 200 && resp.StatusCode < 400 {
+		return nil
+	}
+
+	apiError := Error{Code: int32(resp.StatusCode)}
+
+	err := json.Unmarshal(body, &apiError)
+	if err != nil {
+		// Use the full body as the message if we fail to decode a response.
+		apiError.Message = string(body)
+	}
+
+	return apiError
+}
+
+func (c *Client) do(ctx context.Context, method string, path string, stream bool, reqData any, respData any) error {
+	var reqBody io.Reader
+	var data []byte
+	var err error
+	if reqData != nil {
+		data, err = json.Marshal(reqData)
+		if err != nil {
+			return err
+		}
+		reqBody = bytes.NewReader(data)
+	}
+
+	url := fmt.Sprintf("%s%s", c.URL, path)
+
+	req, err := http.NewRequestWithContext(ctx, method, url, reqBody)
+	if err != nil {
+		return err
+	}
+
+	if c.PrivateKey != nil {
+		s := signature.SignatureData{
+			Method: method,
+			Path:   url,
+			Data:   data,
+		}
+		authHeader, err := signature.SignAuthData(s, c.PrivateKey)
+		if err != nil {
+			return err
+		}
+		req.Header.Set("Authorization", authHeader)
+	}
+
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Accept", "application/json")
+
+	for k, v := range c.Headers {
+		req.Header[k] = v
+	}
+
+	respObj, err := c.HTTP.Do(req)
+	if err != nil {
+		return err
+	}
+	defer respObj.Body.Close()
+
+	respBody, err := io.ReadAll(respObj.Body)
+	if err != nil {
+		return err
+	}
+
+	if err := checkError(respObj, respBody); err != nil {
+		return err
+	}
+
+	if len(respBody) > 0 && respData != nil {
+		if err := json.Unmarshal(respBody, respData); err != nil {
+			return err
+		}
+	}
+	return nil
+}

api/types.go

+package api
+
+import (
+	"fmt"
+	"net/http"
+	"strings"
+)
+
+type Error struct {
+	Code    int32  `json:"code"`
+	Message string `json:"message"`
+}
+
+func (e Error) Error() string {
+	if e.Message == "" {
+		return fmt.Sprintf("%d %v", e.Code, strings.ToLower(http.StatusText(int(e.Code))))
+	}
+	return e.Message
+}
+
+type GenerateRequest struct {
+	Model  string `json:"model"`
+	Prompt string `json:"prompt"`
+}
+
+type GenerateResponse struct {
+	Response string `json:"response"`
+}

cmd/cmd.go

+package cmd
+
+import (
+	"context"
+	"fmt"
+	"io/ioutil"
+	"log"
+	"net"
+	"net/http"
+	"os"
+	"path"
+	"time"
+
+	"github.com/spf13/cobra"
+
+	"github.com/ollama/ollama/api"
+	"github.com/ollama/ollama/server"
+)
+
+func NewAPIClient(cmd *cobra.Command) (*api.Client, error) {
+	var rawKey []byte
+	var err error
+
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return nil, err
+	}
+
+	socket := path.Join(home, ".ollama", "ollama.sock")
+
+	dialer := &net.Dialer{
+		Timeout: 10 * time.Second,
+	}
+
+	k, _ := cmd.Flags().GetString("key")
+
+	if k != "" {
+		fn := path.Join(home, ".ollama/keys/", k)
+		rawKey, err = ioutil.ReadFile(fn)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	return &api.Client{
+		URL: "http://localhost",
+		HTTP: http.Client{
+			Transport: &http.Transport{
+				DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
+					return dialer.DialContext(ctx, "unix", socket)
+				},
+			},
+		},
+		PrivateKey: rawKey,
+	}, nil
+}
+
+func NewCLI() *cobra.Command {
+	log.SetFlags(log.LstdFlags | log.Lshortfile)
+
+	rootCmd := &cobra.Command{
+		Use:   "gollama",
+		Short: "Run any large language model on any machine.",
+		CompletionOptions: cobra.CompletionOptions{
+			DisableDefaultCmd: true,
+		},
+		PersistentPreRun: func(cmd *cobra.Command, args []string) {
+			// Disable usage printing on errors
+			cmd.SilenceUsage = true
+		},
+	}
+
+	rootCmd.PersistentFlags().StringP("key", "k", "", "Private key to use for authenticating")
+
+	cobra.EnableCommandSorting = false
+
+	modelsCmd := &cobra.Command{
+		Use:   "models",
+		Args:  cobra.MaximumNArgs(1),
+		Short: "List models",
+		Long:  "List the models",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			client, err := NewAPIClient(cmd)
+			if err != nil {
+				return err
+			}
+			fmt.Printf("client = %q\n", client)
+			return nil
+		},
+	}
+
+/*
+	runCmd := &cobra.Command{
+		Use: "run",
+		Short: "Run a model and submit prompts.",
+		RunE: func(cmd *cobra.Command. args []string) error {
+		},
+	}
+*/
+
+	serveCmd := &cobra.Command{
+		Use:     "serve",
+		Aliases: []string{"start"},
+		Short:   "Start ollama",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			home, err := os.UserHomeDir()
+			if err != nil {
+				return err
+			}
+
+			socket := path.Join(home, ".ollama", "ollama.sock")
+			if err := os.MkdirAll(path.Dir(socket), 0o700); err != nil {
+				return err
+			}
+
+			if err := os.RemoveAll(socket); err != nil {
+				return err
+			}
+
+			ln, err := net.Listen("unix", socket)
+			if err != nil {
+				return err
+			}
+
+			if err := os.Chmod(socket, 0o700); err != nil {
+				return err
+			}
+
+			return server.Serve(ln)
+		},
+	}
+
+	rootCmd.AddCommand(
+		modelsCmd,
+		serveCmd,
+	)
+
+	return rootCmd
+}

go.mod

+module github.com/ollama/ollama
+
+go 1.20
+
+require (
+	github.com/gin-gonic/gin v1.9.1
+	github.com/go-skynet/go-llama.cpp v0.0.0-20230630201504-ecd358d2f144
+	github.com/r3labs/sse v0.0.0-20210224172625-26fe804710bc
+	github.com/spf13/cobra v1.7.0
+	golang.org/x/crypto v0.10.0
+)
+
+require (
+	github.com/bytedance/sonic v1.9.1 // indirect
+	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
+	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
+	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/go-playground/locales v0.14.1 // indirect
+	github.com/go-playground/universal-translator v0.18.1 // indirect
+	github.com/go-playground/validator/v10 v10.14.0 // indirect
+	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/inconshreveable/mousetrap v1.1.0 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
+	github.com/leodido/go-urn v1.2.4 // indirect
+	github.com/mattn/go-isatty v0.0.19 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/spf13/pflag v1.0.5 // indirect
+	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
+	github.com/ugorji/go/codec v1.2.11 // indirect
+	golang.org/x/arch v0.3.0 // indirect
+	golang.org/x/net v0.10.0 // indirect
+	golang.org/x/sys v0.9.0 // indirect
+	golang.org/x/text v0.10.0 // indirect
+	google.golang.org/protobuf v1.30.0 // indirect
+	gopkg.in/cenkalti/backoff.v1 v1.1.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

go.sum

+github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
+github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
+github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
+github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
+github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
+github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
+github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
+github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
+github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
+github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
+github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
+github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
+github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
+github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
+github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
+github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
+github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
+github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230630201504-ecd358d2f144 h1:fszkmZG3pW9/bqhuWB6sfJMArJPx1RPzjZSqNdhuSQ0=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230630201504-ecd358d2f144/go.mod h1:tzi97YvT1bVQ+iTG39LvpDkKG1WbizgtljC+orSoM40=
+github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
+github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
+github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
+github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
+github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
+github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
+github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
+github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
+github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
+github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
+github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
+github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
+github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/r3labs/sse v0.0.0-20210224172625-26fe804710bc/go.mod h1:S8xSOnV3CgpNrWd0GQ/OoQfMtlg2uPRSuTzcSGrzwK8=
+github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/spf13/cobra v1.7.0 h1:hyqWnYt1ZQShIddO5kBpj3vu05/++x6tJ6dg8EC572I=
+github.com/spf13/cobra v1.7.0/go.mod h1:uLxZILRyS/50WlhOIKD7W6V5bgeIt+4sICxh6uRMrb0=
+github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
+github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
+github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
+github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
+github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
+golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.10.0 h1:LKqV2xt9+kDzSTfOhx4FrkEBcMrAgHSYgzywV9zcGmM=
+golang.org/x/crypto v0.10.0/go.mod h1:o4eNf7Ede1fv+hwOwZsTHl9EsPFO6q6ZvYR8vYfY45I=
+golang.org/x/net v0.0.0-20191116160921-f9c825593386/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.9.0 h1:KS/R3tvhPqvJvwcKfnBHJwwthS11LRhmM5D59eEXa0s=
+golang.org/x/sys v0.9.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.10.0 h1:UpjohKhiEgNc0CSauXmwYftY1+LlaC75SJwh0SgCX58=
+golang.org/x/text v0.10.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
+google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
+google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+gopkg.in/cenkalti/backoff.v1 v1.1.0/go.mod h1:J6Vskwqd+OMVJl8C33mmtxTBs2gyzfv7UDAkHu8BrjI=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

lib/.gitignore

+build

lib/CMakeLists.txt

+cmake_minimum_required(VERSION 3.10) 
+include(FetchContent)
+
+FetchContent_Declare(
+    llama_cpp
+    GIT_REPOSITORY https://github.com/ggerganov/llama.cpp.git
+    GIT_TAG        master
+)
+
+FetchContent_MakeAvailable(llama_cpp)
+
+project(binding)
+
+set(LLAMA_METAL ON CACHE BOOL "Enable Llama Metal by default on macOS")
+
+add_library(binding binding.cpp ${llama_cpp_SOURCE_DIR}/examples/common.cpp)
+target_compile_features(binding PRIVATE cxx_std_11)
+target_include_directories(binding PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
+target_include_directories(binding PRIVATE ${llama_cpp_SOURCE_DIR})
+target_include_directories(binding PRIVATE ${llama_cpp_SOURCE_DIR}/examples)
+target_link_libraries(binding llama ggml_static)

lib/README.md

+# Bindings
+
+These are Llama.cpp bindings
+
+## Build
+
+```
+cmake -S . -B build
+cmake --build build
+```

lib/binding.h

+#ifdef __cplusplus
+#include <vector>
+#include <string>
+extern "C" {
+#endif
+
+#include <stdbool.h>
+
+extern unsigned char tokenCallback(void *, char *);
+
+int load_state(void *ctx, char *statefile, char*modes);
+
+int eval(void* params_ptr, void *ctx, char*text);
+
+void save_state(void *ctx, char *dst, char*modes);
+
+void* load_model(const char *fname, int n_ctx, int n_seed, bool memory_f16, bool mlock, bool embeddings, bool mmap, bool low_vram, bool vocab_only, int n_gpu, int n_batch, const char *maingpu, const char *tensorsplit, bool numa);
+
+int get_embeddings(void* params_ptr, void* state_pr, float * res_embeddings);
+
+int get_token_embeddings(void* params_ptr, void* state_pr,  int *tokens, int tokenSize, float * res_embeddings);
+
+void* llama_allocate_params(const char *prompt, int seed, int threads, int tokens,
+                            int top_k, float top_p, float temp, float repeat_penalty, 
+                            int repeat_last_n, bool ignore_eos, bool memory_f16, 
+                            int n_batch, int n_keep, const char** antiprompt, int antiprompt_count,
+                            float tfs_z, float typical_p, float frequency_penalty, float presence_penalty, int mirostat, float mirostat_eta, float mirostat_tau, bool penalize_nl, const char *logit_bias, const char *session_file, bool prompt_cache_all, bool mlock, bool mmap, const char *maingpu, const char *tensorsplit , bool prompt_cache_ro);
+
+void llama_free_params(void* params_ptr);
+
+void llama_binding_free_model(void* state);
+
+int llama_predict(void* params_ptr, void* state_pr, char* result, bool debug);
+
+#ifdef __cplusplus
+}
+
+
+std::vector<std::string> create_vector(const char** strings, int count);
+void delete_vector(std::vector<std::string>* vec);
+#endif

main.go

+package main
+
+import (
+	"github.com/ollama/ollama/cmd"
+)
+
+func main() {
+	cmd.NewCLI().Execute()
+}

python/README.md

+# Ollama Python bindings
+
+```
+pip install ollama
+```
+
+## Developing
+
+Ollama is built using Python 3 and uses [Poetry](https://python-poetry.org/) to manage dependencies and build packages.
+
+```
+pip install poetry
+```
+
+Install ollama and its dependencies:
+
+```
+poetry install --extras server --with dev
+```
+
+Run ollama server:
+
+```
+poetry run ollama server
+```
+
+Update dependencies:
+
+```
+poetry update --extras server --with dev
+poetry lock
+poetry export >requirements.txt
+```
+
+Build binary package:
+
+```
+poetry build
+```