baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

api: fill up API documentation (#3596)

Browse source 
* api: fill up API documentation

Followup for #2878

Now that the documentation is more complete, mention it in the README.

Updates #2840

* fix typo/lint

* Update README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

---------

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
This commit is contained in:
Eli Bendersky 2024-05-07 16:27:46 -07:00 committed by GitHub
parent 2a5302a1cf
commit d77c1c5f9d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 100 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
api/client.go
View file

@ -1,9 +1,16 @@
// Package api implements the client-side API for code wishing to interact
// with the ollama service. The methods of the [Client] type correspond to
// the ollama REST API as described in https://github.com/ollama/ollama/blob/main/docs/api.md
//
// the ollama REST API as described in [the API documentation].
// The ollama command-line client itself uses this package to interact with
// the backend service.
//
// # Examples
//
// Several examples of using this package are available [in the GitHub
// repository].
//
// [the API documentation]: https://github.com/ollama/ollama/blob/main/docs/api.md
// [in the GitHub repository]: https://github.com/ollama/ollama/tree/main/examples
package api
import (
@ -299,8 +306,14 @@ func (c *Client) Pull(ctx context.Context, req *PullRequest, fn PullProgressFunc
})
}
// PushProgressFunc is a function that [Client.Push] invokes when progress is
// made.
// It's similar to other progress function types like [PullProgressFunc].
type PushProgressFunc func(ProgressResponse) error
// Push uploads a model to the model library; requires registering for ollama.ai
// and adding a public key first. fn is called each time progress is made on
// the request and can be used to display a progress bar, etc.
func (c *Client) Push(ctx context.Context, req *PushRequest, fn PushProgressFunc) error {
return c.stream(ctx, http.MethodPost, "/api/push", req, func(bts []byte) error {
var resp ProgressResponse
@ -312,8 +325,15 @@ func (c *Client) Push(ctx context.Context, req *PushRequest, fn PushProgressFunc
})
}
// CreateProgressFunc is a function that [Client.Create] invokes when progress
// is made.
// It's similar to other progress function types like [PullProgressFunc].
type CreateProgressFunc func(ProgressResponse) error
// Create creates a model from a [Modelfile]. fn is a progress function that
// behaves similarly to other methods (see [Client.Pull]).
//
// [Modelfile]: https://github.com/ollama/ollama/blob/main/docs/modelfile.md
func (c *Client) Create(ctx context.Context, req *CreateRequest, fn CreateProgressFunc) error {
return c.stream(ctx, http.MethodPost, "/api/create", req, func(bts []byte) error {
var resp ProgressResponse
@ -325,6 +345,7 @@ func (c *Client) Create(ctx context.Context, req *CreateRequest, fn CreateProgre
})
}
// List lists models that are available locally.
func (c *Client) List(ctx context.Context) (*ListResponse, error) {
var lr ListResponse
if err := c.do(ctx, http.MethodGet, "/api/tags", nil, &lr); err != nil {
@ -333,6 +354,8 @@ func (c *Client) List(ctx context.Context) (*ListResponse, error) {
return &lr, nil
}
// Copy copies a model - creating a model with another name from an existing
// model.
func (c *Client) Copy(ctx context.Context, req *CopyRequest) error {
if err := c.do(ctx, http.MethodPost, "/api/copy", req, nil); err != nil {
return err
@ -340,6 +363,7 @@ func (c *Client) Copy(ctx context.Context, req *CopyRequest) error {
return nil
}
// Delete deletes a model and its data.
func (c *Client) Delete(ctx context.Context, req *DeleteRequest) error {
if err := c.do(ctx, http.MethodDelete, "/api/delete", req, nil); err != nil {
return err
@ -347,6 +371,7 @@ func (c *Client) Delete(ctx context.Context, req *DeleteRequest) error {
return nil
}
// Show obtains model information, including details, modelfile, license etc.
func (c *Client) Show(ctx context.Context, req *ShowRequest) (*ShowResponse, error) {
var resp ShowResponse
if err := c.do(ctx, http.MethodPost, "/api/show", req, &resp); err != nil {
@ -355,12 +380,16 @@ func (c *Client) Show(ctx context.Context, req *ShowRequest) (*ShowResponse, err
return &resp, nil
}
// Hearbeat checks if the server has started and is responsive; if yes, it
// returns nil, otherwise an error.
func (c *Client) Heartbeat(ctx context.Context) error {
if err := c.do(ctx, http.MethodHead, "/", nil, nil); err != nil {
return err
}
return nil
}
// Embeddings generates embeddings 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 {
@ -369,10 +398,13 @@ func (c *Client) Embeddings(ctx context.Context, req *EmbeddingRequest) (*Embedd
return &resp, nil
}
// CreateBlob creates a blob from a file on the server. digest is the
// expected SHA256 digest of the file, and r represents the file.
func (c *Client) CreateBlob(ctx context.Context, digest string, r io.Reader) error {
return c.do(ctx, http.MethodPost, fmt.Sprintf("/api/blobs/%s", digest), r, nil)
}
// Version returns the Ollama server version as a string.
func (c *Client) Version(ctx context.Context) (string, error) {
var version struct {
Version string `json:"version"`

58
api/types.go
View file

@ -12,6 +12,7 @@ import (
"time"
)
// StatusError is an error with and HTTP status code.
type StatusError struct {
StatusCode int
Status string
@ -32,6 +33,7 @@ func (e StatusError) Error() string {
}
}
// ImageData represents the raw binary data of an image file.
type ImageData []byte
// GenerateRequest describes a request sent by [Client.Generate]. While you
@ -77,22 +79,39 @@ type GenerateRequest struct {
Options map[string]interface{} `json:"options"`
}
// ChatRequest describes a request sent by [Client.Chat].
type ChatRequest struct {
// Model is the model name, as in [GenerateRequest].
Model string `json:"model"`
// Messages is the messages of the chat - can be used to keep a chat memory.
Messages []Message `json:"messages"`
// Stream enable streaming of returned response; true by default.
Stream *bool `json:"stream,omitempty"`
// Format is the format to return the response in (e.g. "json").
Format string `json:"format"`
// KeepAlive controls how long the model will stay loaded into memory
// followin the request.
KeepAlive *Duration `json:"keep_alive,omitempty"`
// Options lists model-specific options.
Options map[string]interface{} `json:"options"`
}
// 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"` // one of ["system", "user", "assistant"]
Role string `json:"role"`
Content string `json:"content"`
Images []ImageData `json:"images,omitempty"`
}
// ChatResponse is the response returned by [Client.Chat]. Its fields are
// similar to [GenerateResponse].
type ChatResponse struct {
Model string `json:"model"`
CreatedAt time.Time `json:"created_at"`
@ -112,7 +131,8 @@ type Metrics struct {
EvalDuration time.Duration `json:"eval_duration,omitempty"`
}
// Options specified in GenerateRequest, if you add a new option here add it to the API docs also
// Options specified in [GenerateRequest], if you add a new option here add it
// to the API docs also.
type Options struct {
Runner
@ -158,18 +178,28 @@ type Runner struct {
RopeFrequencyScale float32 `json:"rope_frequency_scale,omitempty"`
}
// EmbeddingRequest is the request passed to [Client.Embeddings].
type EmbeddingRequest struct {
// Model is the model name.
Model string `json:"model"`
// Prompt is the textual prompt to embed.
Prompt string `json:"prompt"`
// KeepAlive controls how long the model will stay loaded in memory following
// this request.
KeepAlive *Duration `json:"keep_alive,omitempty"`
// Options lists model-specific options.
Options map[string]interface{} `json:"options"`
}
// EmbeddingResponse is the response from [Client.Embeddings].
type EmbeddingResponse struct {
Embedding []float64 `json:"embedding"`
}
// CreateRequest is the request passed to [Client.Create].
type CreateRequest struct {
Model string `json:"model"`
Path string `json:"path"`
@ -181,6 +211,7 @@ type CreateRequest struct {
Name string `json:"name"`
}
// DeleteRequest is the request passed to [Client.Delete].
type DeleteRequest struct {
Model string `json:"model"`
@ -188,6 +219,7 @@ type DeleteRequest struct {
Name string `json:"name"`
}
// ShowRequest is the request passed to [Client.Show].
type ShowRequest struct {
Model string `json:"model"`
System string `json:"system"`
@ -199,6 +231,7 @@ type ShowRequest struct {
Name string `json:"name"`
}
// ShowResponse is the response returned from [Client.Show].
type ShowResponse struct {
License string `json:"license,omitempty"`
Modelfile string `json:"modelfile,omitempty"`
@ -209,11 +242,13 @@ type ShowResponse struct {
Messages []Message `json:"messages,omitempty"`
}
// CopyRequest is the request passed to [Client.Copy].
type CopyRequest struct {
Source string `json:"source"`
Destination string `json:"destination"`
}
// PullRequest is the request passed to [Client.Pull].
type PullRequest struct {
Model string `json:"model"`
Insecure bool `json:"insecure,omitempty"`
@ -225,6 +260,8 @@ type PullRequest struct {
Name string `json:"name"`
}
// ProgressResponse is the response passed to progress functions like
// [PullProgressFunc] and [PushProgressFunc].
type ProgressResponse struct {
Status string `json:"status"`
Digest string `json:"digest,omitempty"`
@ -232,6 +269,7 @@ type ProgressResponse struct {
Completed int64 `json:"completed,omitempty"`
}
// PushRequest is the request passed to [Client.Push].
type PushRequest struct {
Model string `json:"model"`
Insecure bool `json:"insecure,omitempty"`
@ -243,10 +281,12 @@ type PushRequest struct {
Name string `json:"name"`
}
// ListResponse is the response from [Client.List].
type ListResponse struct {
Models []ModelResponse `json:"models"`
}
// ModelResponse is a single model description in [ListResponse].
type ModelResponse struct {
Name string `json:"name"`
Model string `json:"model"`
@ -260,17 +300,28 @@ type TokenResponse struct {
Token string `json:"token"`
}
// GenerateResponse is the response passed into [GenerateResponseFunc].
type GenerateResponse struct {
// Model is the model name that generated the response.
Model string `json:"model"`
//CreatedAt is the timestamp of the response.
CreatedAt time.Time `json:"created_at"`
// Response is the textual response itself.
Response string `json:"response"`
// Done specifies if the response is complete.
Done bool `json:"done"`
// Context is an encoding of the conversation used in this response; this
// can be sent in the next request to keep a conversational memory.
Context []int `json:"context,omitempty"`
Metrics
}
// ModelDetails provides details about a model.
type ModelDetails struct {
ParentModel string `json:"parent_model"`
Format string `json:"format"`
@ -308,6 +359,7 @@ func (m *Metrics) Summary() {
}
}
// ErrInvalidOpts is returned when invalid options are passed to the client.
var ErrInvalidOpts = errors.New("invalid options")
var ErrInvalidHostPort = errors.New("invalid port specified in OLLAMA_HOST")
@ -394,6 +446,8 @@ func (opts *Options) FromMap(m map[string]interface{}) error {
return nil
}
// DefaultOptions is the default set of options for [GenerateRequest]; these
// values are used unless the user specifies other values explicitly.
func DefaultOptions() Options {
return Options{
// options set on request to runner