highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-07-28 12:23:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Revert "chat api (#991)" while context variable is fixed

Browse Source 
This reverts commit 7a0899d62d.
This commit is contained in:
Jeffrey Morgan
2023-12-04 21:16:27 -08:00
parent f1ef3f9947
commit 00d06619a1
8 changed files with 144 additions and 559 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
api/client.go
View File

@@ -221,19 +221,6 @@ func (c *Client) Generate(ctx context.Context, req *GenerateRequest, fn Generate
})
}
type ChatResponseFunc func(ChatResponse) error
func (c *Client) Chat(ctx context.Context, req *ChatRequest, fn ChatResponseFunc) error {
return c.stream(ctx, http.MethodPost, "/api/chat", req, func(bts []byte) error {
var resp ChatResponse
if err := json.Unmarshal(bts, &resp); err != nil {
return err
}
return fn(resp)
})
}
type PullProgressFunc func(ProgressResponse) error
func (c *Client) Pull(ctx context.Context, req *PullRequest, fn PullProgressFunc) error {

74
api/types.go
View File

@@ -36,7 +36,7 @@ type GenerateRequest struct {
Prompt string `json:"prompt"`
System string `json:"system"`
Template string `json:"template"`
Context []int `json:"context,omitempty"` // DEPRECATED: context is deprecated, use the /chat endpoint instead for chat history
Context []int `json:"context,omitempty"`
Stream *bool `json:"stream,omitempty"`
Raw bool `json:"raw,omitempty"`
Format string `json:"format"`
@@ -44,41 +44,6 @@ type GenerateRequest struct {
Options map[string]interface{} `json:"options"`
}
type ChatRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`
Template string `json:"template"`
Stream *bool `json:"stream,omitempty"`
Format string `json:"format"`
Options map[string]interface{} `json:"options"`
}
type Message struct {
Role string `json:"role"` // one of ["system", "user", "assistant"]
Content string `json:"content"`
}
type ChatResponse struct {
Model string `json:"model"`
CreatedAt time.Time `json:"created_at"`
Message *Message `json:"message,omitempty"`
Done bool `json:"done"`
Context []int `json:"context,omitempty"`
EvalMetrics
}
type EvalMetrics struct {
TotalDuration time.Duration `json:"total_duration,omitempty"`
LoadDuration time.Duration `json:"load_duration,omitempty"`
PromptEvalCount int `json:"prompt_eval_count,omitempty"`
PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
EvalCount int `json:"eval_count,omitempty"`
EvalDuration time.Duration `json:"eval_duration,omitempty"`
}
// Options specfied in GenerateRequest, if you add a new option here add it to the API docs also
type Options struct {
Runner
@@ -208,34 +173,39 @@ type GenerateResponse struct {
Done bool `json:"done"`
Context []int `json:"context,omitempty"`
EvalMetrics
TotalDuration time.Duration `json:"total_duration,omitempty"`
LoadDuration time.Duration `json:"load_duration,omitempty"`
PromptEvalCount int `json:"prompt_eval_count,omitempty"`
PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
EvalCount int `json:"eval_count,omitempty"`
EvalDuration time.Duration `json:"eval_duration,omitempty"`
}
func (m *EvalMetrics) Summary() {
if m.TotalDuration > 0 {
fmt.Fprintf(os.Stderr, "total duration: %v\n", m.TotalDuration)
func (r *GenerateResponse) Summary() {
if r.TotalDuration > 0 {
fmt.Fprintf(os.Stderr, "total duration: %v\n", r.TotalDuration)
}
if m.LoadDuration > 0 {
fmt.Fprintf(os.Stderr, "load duration: %v\n", m.LoadDuration)
if r.LoadDuration > 0 {
fmt.Fprintf(os.Stderr, "load duration: %v\n", r.LoadDuration)
}
if m.PromptEvalCount > 0 {
fmt.Fprintf(os.Stderr, "prompt eval count: %d token(s)\n", m.PromptEvalCount)
if r.PromptEvalCount > 0 {
fmt.Fprintf(os.Stderr, "prompt eval count: %d token(s)\n", r.PromptEvalCount)
}
if m.PromptEvalDuration > 0 {
fmt.Fprintf(os.Stderr, "prompt eval duration: %s\n", m.PromptEvalDuration)
fmt.Fprintf(os.Stderr, "prompt eval rate: %.2f tokens/s\n", float64(m.PromptEvalCount)/m.PromptEvalDuration.Seconds())
if r.PromptEvalDuration > 0 {
fmt.Fprintf(os.Stderr, "prompt eval duration: %s\n", r.PromptEvalDuration)
fmt.Fprintf(os.Stderr, "prompt eval rate: %.2f tokens/s\n", float64(r.PromptEvalCount)/r.PromptEvalDuration.Seconds())
}
if m.EvalCount > 0 {
fmt.Fprintf(os.Stderr, "eval count: %d token(s)\n", m.EvalCount)
if r.EvalCount > 0 {
fmt.Fprintf(os.Stderr, "eval count: %d token(s)\n", r.EvalCount)
}
if m.EvalDuration > 0 {
fmt.Fprintf(os.Stderr, "eval duration: %s\n", m.EvalDuration)
fmt.Fprintf(os.Stderr, "eval rate: %.2f tokens/s\n", float64(m.EvalCount)/m.EvalDuration.Seconds())
if r.EvalDuration > 0 {
fmt.Fprintf(os.Stderr, "eval duration: %s\n", r.EvalDuration)
fmt.Fprintf(os.Stderr, "eval rate: %.2f tokens/s\n", float64(r.EvalCount)/r.EvalDuration.Seconds())
}
}