mirror of
https://github.com/mayswind/ezbookkeeping.git
synced 2026-05-19 17:24:26 +08:00
create transactions from AI receipt image recognition results
This commit is contained in:
MaysWind
@@ -0,0 +1,91 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"crypto/tls"
|
||||
"io"
|
||||
"net/http"
|
||||
"time"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/errs"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/log"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/utils"
|
||||
)
|
||||
|
||||
// HttpLargeLanguageModelProvider defines the structure of http large language model provider
|
||||
type HttpLargeLanguageModelProvider interface {
|
||||
// BuildTextualRequest returns the http request by the provider api definition
|
||||
BuildTextualRequest(c core.Context, uid int64, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) (*http.Request, error)
|
||||
|
||||
// ParseTextualResponse returns the textual response entity by the provider api definition
|
||||
ParseTextualResponse(c core.Context, uid int64, body []byte, responseType LargeLanguageModelResponseFormat) (*LargeLanguageModelTextualResponse, error)
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id if supported, otherwise returns empty string
|
||||
GetReceiptImageRecognitionModelID() string
|
||||
}
|
||||
|
||||
// CommonHttpLargeLanguageModelProvider defines the structure of common http large language model provider
|
||||
type CommonHttpLargeLanguageModelProvider struct {
|
||||
LargeLanguageModelProvider
|
||||
provider HttpLargeLanguageModelProvider
|
||||
}
|
||||
|
||||
// GetJsonResponseByReceiptImageRecognitionModel returns the json response from the OpenAI common compatible large language model provider
|
||||
func (p *CommonHttpLargeLanguageModelProvider) GetJsonResponseByReceiptImageRecognitionModel(c core.Context, uid int64, currentConfig *settings.Config, request *LargeLanguageModelRequest) (*LargeLanguageModelTextualResponse, error) {
|
||||
return p.getTextualResponse(c, uid, currentConfig, request, p.provider.GetReceiptImageRecognitionModelID(), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
}
|
||||
|
||||
func (p *CommonHttpLargeLanguageModelProvider) getTextualResponse(c core.Context, uid int64, currentConfig *settings.Config, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) (*LargeLanguageModelTextualResponse, error) {
|
||||
if modelId == "" {
|
||||
return nil, errs.ErrInvalidLLMModelId
|
||||
}
|
||||
|
||||
transport := http.DefaultTransport.(*http.Transport).Clone()
|
||||
utils.SetProxyUrl(transport, currentConfig.LargeLanguageModelAPIProxy)
|
||||
|
||||
if currentConfig.LargeLanguageModelAPISkipTLSVerify {
|
||||
transport.TLSClientConfig = &tls.Config{
|
||||
InsecureSkipVerify: true,
|
||||
}
|
||||
}
|
||||
|
||||
client := &http.Client{
|
||||
Transport: transport,
|
||||
Timeout: time.Duration(currentConfig.LargeLanguageModelAPIRequestTimeout) * time.Millisecond,
|
||||
}
|
||||
|
||||
httpRequest, err := p.provider.BuildTextualRequest(c, uid, request, modelId, responseType)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[http_large_language_model_provider.getTextualResponse] failed to build requests for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
httpRequest.Header.Set("User-Agent", settings.GetUserAgent())
|
||||
|
||||
resp, err := client.Do(httpRequest)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[http_large_language_model_provider.getTextualResponse] failed to request large language model api for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
defer resp.Body.Close()
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
|
||||
log.Debugf(c, "[http_large_language_model_provider.getTextualResponse] response is %s", body)
|
||||
|
||||
if resp.StatusCode != 200 {
|
||||
log.Errorf(c, "[http_large_language_model_provider.getTextualResponse] failed to get large language model api response for user \"uid:%d\", because response code is %d", uid, resp.StatusCode)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
return p.provider.ParseTextualResponse(c, uid, body, responseType)
|
||||
}
|
||||
|
||||
func newCommonHttpLargeLanguageModelProvider(provider HttpLargeLanguageModelProvider) *CommonHttpLargeLanguageModelProvider {
|
||||
return &CommonHttpLargeLanguageModelProvider{
|
||||
provider: provider,
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
package llm
|
||||
|
||||
import "reflect"
|
||||
|
||||
type LargeLanguageModelRequestPromptType byte
|
||||
|
||||
// Large Language Model Request Prompt Type
|
||||
const (
|
||||
LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_TEXT LargeLanguageModelRequestPromptType = 0
|
||||
LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_IMAGE_URL LargeLanguageModelRequestPromptType = 1
|
||||
)
|
||||
|
||||
type LargeLanguageModelResponseFormat byte
|
||||
|
||||
// Large Language Model Response Format
|
||||
const (
|
||||
LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_TEXT LargeLanguageModelResponseFormat = 0
|
||||
LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON LargeLanguageModelResponseFormat = 1
|
||||
)
|
||||
|
||||
// LargeLanguageModelRequest represents a request to a large language model
|
||||
type LargeLanguageModelRequest struct {
|
||||
Stream bool
|
||||
SystemPrompt string
|
||||
UserPrompt []byte
|
||||
UserPromptType LargeLanguageModelRequestPromptType
|
||||
ResponseJsonObjectType reflect.Type
|
||||
}
|
||||
|
||||
// LargeLanguageModelTextualResponse represents a textual response from a large language model
|
||||
type LargeLanguageModelTextualResponse struct {
|
||||
Content string
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
// LargeLanguageModelProvider defines the structure of large language model provider
|
||||
type LargeLanguageModelProvider interface {
|
||||
// GetJsonResponseByReceiptImageRecognitionModel returns the json response from the large language model provider by receipt image recognition model
|
||||
GetJsonResponseByReceiptImageRecognitionModel(c core.Context, uid int64, currentConfig *settings.Config, request *LargeLanguageModelRequest) (*LargeLanguageModelTextualResponse, error)
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/errs"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
// LargeLanguageModelProviderContainer contains the current large language model provider
|
||||
type LargeLanguageModelProviderContainer struct {
|
||||
current LargeLanguageModelProvider
|
||||
}
|
||||
|
||||
// Initialize a large language model provider container singleton instance
|
||||
var (
|
||||
Container = &LargeLanguageModelProviderContainer{}
|
||||
)
|
||||
|
||||
// InitializeLargeLanguageModelProvider initializes the current large language model provider according to the config
|
||||
func InitializeLargeLanguageModelProvider(config *settings.Config) error {
|
||||
if config.LLMProvider == settings.OpenAILLMProvider {
|
||||
Container.current = NewOpenAILargeLanguageModelProvider(config)
|
||||
return nil
|
||||
} else if config.LLMProvider == settings.OpenAICompatibleLLMProvider {
|
||||
Container.current = NewOpenAICompatibleLargeLanguageModelProvider(config)
|
||||
return nil
|
||||
} else if config.LLMProvider == settings.OpenRouterLLMProvider {
|
||||
Container.current = NewOpenRouterLargeLanguageModelProvider(config)
|
||||
return nil
|
||||
} else if config.LLMProvider == settings.OllamaLLMProvider {
|
||||
Container.current = NewOllamaLargeLanguageModelProvider(config)
|
||||
return nil
|
||||
}
|
||||
|
||||
return errs.ErrInvalidLLMProvider
|
||||
}
|
||||
|
||||
// GetJsonResponseByReceiptImageRecognitionModel returns the json response from the current large language model provider by receipt image recognition model
|
||||
func (l *LargeLanguageModelProviderContainer) GetJsonResponseByReceiptImageRecognitionModel(c core.Context, uid int64, currentConfig *settings.Config, request *LargeLanguageModelRequest) (*LargeLanguageModelTextualResponse, error) {
|
||||
if Container.current == nil {
|
||||
return nil, errs.ErrInvalidLLMProvider
|
||||
}
|
||||
|
||||
return l.current.GetJsonResponseByReceiptImageRecognitionModel(c, uid, currentConfig, request)
|
||||
}
|
||||
@@ -0,0 +1,153 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"net/http"
|
||||
"strings"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/errs"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/log"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
const ollamaChatCompletionsPath = "api/chat"
|
||||
|
||||
// OllamaLargeLanguageModelProvider defines the structure of Ollama large language model provider
|
||||
type OllamaLargeLanguageModelProvider struct {
|
||||
CommonHttpLargeLanguageModelProvider
|
||||
OllamaServerURL string
|
||||
ReceiptImageRecognitionModelID string
|
||||
}
|
||||
|
||||
// BuildTextualRequest returns the http request by Ollama provider
|
||||
func (p *OllamaLargeLanguageModelProvider) BuildTextualRequest(c core.Context, uid int64, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) (*http.Request, error) {
|
||||
requestBody, err := p.buildJsonRequestBody(c, uid, request, modelId, responseType)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
httpRequest, err := http.NewRequest("POST", p.getOllamaRequestUrl(), bytes.NewReader(requestBody))
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
httpRequest.Header.Set("Content-Type", "application/json")
|
||||
|
||||
return httpRequest, nil
|
||||
}
|
||||
|
||||
// ParseTextualResponse returns the textual response by Ollama provider
|
||||
func (p *OllamaLargeLanguageModelProvider) ParseTextualResponse(c core.Context, uid int64, body []byte, responseType LargeLanguageModelResponseFormat) (*LargeLanguageModelTextualResponse, error) {
|
||||
responseBody := make(map[string]any)
|
||||
err := json.Unmarshal(body, &responseBody)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[ollama_large_language_model_provider.ParseTextualResponse] failed to parse response for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
message, ok := responseBody["message"].(map[string]any)
|
||||
|
||||
if !ok {
|
||||
log.Errorf(c, "[ollama_large_language_model_provider.ParseTextualResponse] no message found in response for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
content, ok := message["content"].(string)
|
||||
|
||||
if !ok {
|
||||
log.Errorf(c, "[ollama_large_language_model_provider.ParseTextualResponse] no content found in message for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
if responseType == LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON {
|
||||
if strings.HasPrefix(content, "```json") && strings.HasSuffix(content, "```") {
|
||||
content = strings.TrimPrefix(content, "```json")
|
||||
content = strings.TrimSuffix(content, "```")
|
||||
} else if strings.HasPrefix(content, "```") && strings.HasSuffix(content, "```") {
|
||||
content = strings.TrimPrefix(content, "```")
|
||||
content = strings.TrimSuffix(content, "```")
|
||||
}
|
||||
}
|
||||
|
||||
textualResponse := &LargeLanguageModelTextualResponse{
|
||||
Content: content,
|
||||
}
|
||||
|
||||
return textualResponse, nil
|
||||
}
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id of Ollama provider
|
||||
func (p *OllamaLargeLanguageModelProvider) GetReceiptImageRecognitionModelID() string {
|
||||
return p.ReceiptImageRecognitionModelID
|
||||
}
|
||||
|
||||
func (p *OllamaLargeLanguageModelProvider) buildJsonRequestBody(c core.Context, uid int64, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) ([]byte, error) {
|
||||
requestMessages := make([]any, 0)
|
||||
|
||||
if request.SystemPrompt != "" {
|
||||
requestMessages = append(requestMessages, map[string]string{
|
||||
"role": "system",
|
||||
"content": request.SystemPrompt,
|
||||
})
|
||||
}
|
||||
|
||||
if len(request.UserPrompt) > 0 {
|
||||
imageBase64Data := base64.StdEncoding.EncodeToString(request.UserPrompt)
|
||||
if request.UserPromptType == LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_IMAGE_URL {
|
||||
requestMessages = append(requestMessages, map[string]any{
|
||||
"role": "user",
|
||||
"content": "",
|
||||
"images": []string{imageBase64Data},
|
||||
})
|
||||
} else {
|
||||
requestMessages = append(requestMessages, map[string]string{
|
||||
"role": "user",
|
||||
"content": string(request.UserPrompt),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
requestBody := make(map[string]any)
|
||||
requestBody["model"] = modelId
|
||||
requestBody["stream"] = request.Stream
|
||||
requestBody["messages"] = requestMessages
|
||||
|
||||
if responseType == LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON {
|
||||
requestBody["format"] = "json"
|
||||
}
|
||||
|
||||
requestBodyBytes, err := json.Marshal(requestBody)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[ollama_large_language_model_provider.buildJsonRequestBody] failed to marshal request body for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrOperationFailed
|
||||
}
|
||||
|
||||
log.Debugf(c, "[ollama_large_language_model_provider.buildJsonRequestBody] request body is %s", requestBodyBytes)
|
||||
return requestBodyBytes, nil
|
||||
}
|
||||
|
||||
func (p *OllamaLargeLanguageModelProvider) getOllamaRequestUrl() string {
|
||||
url := p.OllamaServerURL
|
||||
|
||||
if url[len(url)-1] != '/' {
|
||||
url += "/"
|
||||
}
|
||||
|
||||
url += ollamaChatCompletionsPath
|
||||
return url
|
||||
}
|
||||
|
||||
// NewOllamaLargeLanguageModelProvider creates a new Ollama large language model provider instance
|
||||
func NewOllamaLargeLanguageModelProvider(config *settings.Config) LargeLanguageModelProvider {
|
||||
return newCommonHttpLargeLanguageModelProvider(&OllamaLargeLanguageModelProvider{
|
||||
OllamaServerURL: config.OllamaServerURL,
|
||||
ReceiptImageRecognitionModelID: config.OllamaReceiptImageRecognitionModelID,
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,138 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
)
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_buildJsonRequestBody_TextualUserPrompt(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
request := &LargeLanguageModelRequest{
|
||||
SystemPrompt: "You are a helpful assistant.",
|
||||
UserPrompt: []byte("Hello, how are you?"),
|
||||
}
|
||||
|
||||
bodyBytes, err := provider.buildJsonRequestBody(core.NewNullContext(), 0, request, "test", LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
|
||||
var body map[string]interface{}
|
||||
err = json.Unmarshal(bodyBytes, &body)
|
||||
assert.Nil(t, err)
|
||||
|
||||
assert.Equal(t, "{\"format\":\"json\",\"messages\":[{\"content\":\"You are a helpful assistant.\",\"role\":\"system\"},{\"content\":\"Hello, how are you?\",\"role\":\"user\"}],\"model\":\"test\",\"stream\":false}", string(bodyBytes))
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_buildJsonRequestBody_ImageUserPrompt(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
request := &LargeLanguageModelRequest{
|
||||
SystemPrompt: "What's in this image?",
|
||||
UserPrompt: []byte("fakedata"),
|
||||
UserPromptType: LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_IMAGE_URL,
|
||||
}
|
||||
|
||||
bodyBytes, err := provider.buildJsonRequestBody(core.NewNullContext(), 0, request, "test", LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
|
||||
var body map[string]interface{}
|
||||
err = json.Unmarshal(bodyBytes, &body)
|
||||
assert.Nil(t, err)
|
||||
|
||||
assert.Equal(t, "{\"format\":\"json\",\"messages\":[{\"content\":\"What's in this image?\",\"role\":\"system\"},{\"content\":\"\",\"images\":[\"ZmFrZWRhdGE=\"],\"role\":\"user\"}],\"model\":\"test\",\"stream\":false}", string(bodyBytes))
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_ParseTextualResponse_ValidJsonResponse(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
response := `{
|
||||
"model": "test",
|
||||
"created_at": "2025-09-01T01:02:03.456789Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
"content": "This is a test response"
|
||||
}
|
||||
}`
|
||||
|
||||
result, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
assert.Equal(t, "This is a test response", result.Content)
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_ParseTextualResponse_EmptyResponse(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
response := `{
|
||||
"model": "test",
|
||||
"created_at": "2025-09-01T01:02:03.456789Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
"content": ""
|
||||
}
|
||||
}`
|
||||
|
||||
result, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
assert.Equal(t, "", result.Content)
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_ParseTextualResponse_EmptyChoices(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
response := `{
|
||||
"model": "test",
|
||||
"created_at": "2025-09-01T01:02:03.456789Z",
|
||||
"message": {}
|
||||
}`
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_ParseTextualResponse_NoChoiceContent(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
response := `{
|
||||
"model": "test",
|
||||
"created_at": "2025-09-01T01:02:03.456789Z",
|
||||
"message": {
|
||||
"role": "assistant"
|
||||
}
|
||||
}`
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_ParseTextualResponse_InvalidJson(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{}
|
||||
|
||||
response := "error"
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
|
||||
func TestOllamaLargeLanguageModelProvider_GetOllamaRequestUrl(t *testing.T) {
|
||||
provider := &OllamaLargeLanguageModelProvider{
|
||||
OllamaServerURL: "http://localhost:11434/",
|
||||
}
|
||||
url := provider.getOllamaRequestUrl()
|
||||
assert.Equal(t, "http://localhost:11434/api/chat", url)
|
||||
|
||||
provider = &OllamaLargeLanguageModelProvider{
|
||||
OllamaServerURL: "http://localhost:11434",
|
||||
}
|
||||
url = provider.getOllamaRequestUrl()
|
||||
assert.Equal(t, "http://localhost:11434/api/chat", url)
|
||||
|
||||
provider = &OllamaLargeLanguageModelProvider{
|
||||
OllamaServerURL: "http://example.com/ollama/",
|
||||
}
|
||||
url = provider.getOllamaRequestUrl()
|
||||
assert.Equal(t, "http://example.com/ollama/api/chat", url)
|
||||
}
|
||||
@@ -0,0 +1,187 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"net/http"
|
||||
"strings"
|
||||
|
||||
"github.com/invopop/jsonschema"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/errs"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/log"
|
||||
)
|
||||
|
||||
// OpenAIChatCompletionsLargeLanguageModelProvider defines the structure of OpenAI chat completions compatible large language model provider
|
||||
type OpenAIChatCompletionsLargeLanguageModelProvider interface {
|
||||
// BuildChatCompletionsHttpRequest returns the chat completions http request
|
||||
BuildChatCompletionsHttpRequest(c core.Context, uid int64) (*http.Request, error)
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id if supported, otherwise returns empty string
|
||||
GetReceiptImageRecognitionModelID() string
|
||||
}
|
||||
|
||||
// OpenAICommonChatCompletionsHttpLargeLanguageModelProvider defines the structure of OpenAI common compatible large language model provider based on chat completions api
|
||||
type OpenAICommonChatCompletionsHttpLargeLanguageModelProvider struct {
|
||||
CommonHttpLargeLanguageModelProvider
|
||||
provider OpenAIChatCompletionsLargeLanguageModelProvider
|
||||
}
|
||||
|
||||
// BuildTextualRequest returns the http request by OpenAI common compatible provider
|
||||
func (p *OpenAICommonChatCompletionsHttpLargeLanguageModelProvider) BuildTextualRequest(c core.Context, uid int64, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) (*http.Request, error) {
|
||||
requestBody, err := p.buildJsonRequestBody(c, uid, request, modelId, responseType)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
httpRequest, err := p.provider.BuildChatCompletionsHttpRequest(c, uid)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
httpRequest.Body = io.NopCloser(bytes.NewReader(requestBody))
|
||||
httpRequest.Header.Set("Content-Type", "application/json")
|
||||
|
||||
return httpRequest, nil
|
||||
}
|
||||
|
||||
// ParseTextualResponse returns the textual response by OpenAI common compatible provider
|
||||
func (p *OpenAICommonChatCompletionsHttpLargeLanguageModelProvider) ParseTextualResponse(c core.Context, uid int64, body []byte, responseType LargeLanguageModelResponseFormat) (*LargeLanguageModelTextualResponse, error) {
|
||||
responseBody := make(map[string]any)
|
||||
err := json.Unmarshal(body, &responseBody)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.ParseTextualResponse] failed to parse response for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
choices, ok := responseBody["choices"].([]any)
|
||||
|
||||
if !ok || len(choices) < 1 {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.ParseTextualResponse] no choices found in response for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
firstChoice, ok := choices[0].(map[string]any)
|
||||
|
||||
if !ok {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.ParseTextualResponse] invalid choice format in response for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
message, ok := firstChoice["message"].(map[string]any)
|
||||
|
||||
if !ok {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.ParseTextualResponse] no message found in choice for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
content, ok := message["content"].(string)
|
||||
|
||||
if !ok {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.ParseTextualResponse] no content found in message for user \"uid:%d\"", uid)
|
||||
return nil, errs.ErrFailedToRequestRemoteApi
|
||||
}
|
||||
|
||||
if responseType == LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON {
|
||||
if strings.HasPrefix(content, "```json") && strings.HasSuffix(content, "```") {
|
||||
content = strings.TrimPrefix(content, "```json")
|
||||
content = strings.TrimSuffix(content, "```")
|
||||
} else if strings.HasPrefix(content, "```") && strings.HasSuffix(content, "```") {
|
||||
content = strings.TrimPrefix(content, "```")
|
||||
content = strings.TrimSuffix(content, "```")
|
||||
}
|
||||
}
|
||||
|
||||
textualResponse := &LargeLanguageModelTextualResponse{
|
||||
Content: content,
|
||||
}
|
||||
|
||||
return textualResponse, nil
|
||||
}
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id of OpenAI common compatible provider
|
||||
func (p *OpenAICommonChatCompletionsHttpLargeLanguageModelProvider) GetReceiptImageRecognitionModelID() string {
|
||||
return p.provider.GetReceiptImageRecognitionModelID()
|
||||
}
|
||||
|
||||
func (p *OpenAICommonChatCompletionsHttpLargeLanguageModelProvider) buildJsonRequestBody(c core.Context, uid int64, request *LargeLanguageModelRequest, modelId string, responseType LargeLanguageModelResponseFormat) ([]byte, error) {
|
||||
requestMessages := make([]any, 0)
|
||||
|
||||
if request.SystemPrompt != "" {
|
||||
requestMessages = append(requestMessages, map[string]string{
|
||||
"role": "system",
|
||||
"content": request.SystemPrompt,
|
||||
})
|
||||
}
|
||||
|
||||
if len(request.UserPrompt) > 0 {
|
||||
if request.UserPromptType == LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_IMAGE_URL {
|
||||
imageBase64Data := "data:image/png;base64," + base64.StdEncoding.EncodeToString(request.UserPrompt)
|
||||
requestMessages = append(requestMessages, map[string]any{
|
||||
"role": "user",
|
||||
"content": []any{
|
||||
core.O{
|
||||
"type": "image_url",
|
||||
"image_url": core.O{
|
||||
"url": imageBase64Data,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
} else {
|
||||
requestMessages = append(requestMessages, map[string]string{
|
||||
"role": "user",
|
||||
"content": string(request.UserPrompt),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
requestBody := make(map[string]any)
|
||||
requestBody["model"] = modelId
|
||||
requestBody["stream"] = request.Stream
|
||||
requestBody["messages"] = requestMessages
|
||||
|
||||
if responseType == LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON {
|
||||
if request.ResponseJsonObjectType != nil {
|
||||
schemeGenerator := jsonschema.Reflector{
|
||||
Anonymous: true,
|
||||
DoNotReference: true,
|
||||
ExpandedStruct: true,
|
||||
}
|
||||
|
||||
schema := schemeGenerator.ReflectFromType(request.ResponseJsonObjectType)
|
||||
schema.Version = ""
|
||||
|
||||
requestBody["response_format"] = core.O{
|
||||
"type": "json_schema",
|
||||
"json_schema": schema,
|
||||
}
|
||||
} else {
|
||||
requestBody["response_format"] = core.O{
|
||||
"type": "json_object",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
requestBodyBytes, err := json.Marshal(requestBody)
|
||||
|
||||
if err != nil {
|
||||
log.Errorf(c, "[openai_common_compatible_large_language_model_provider.buildJsonRequestBody] failed to marshal request body for user \"uid:%d\", because %s", uid, err.Error())
|
||||
return nil, errs.ErrOperationFailed
|
||||
}
|
||||
|
||||
log.Debugf(c, "[openai_common_compatible_large_language_model_provider.buildJsonRequestBody] request body is %s", requestBodyBytes)
|
||||
return requestBodyBytes, nil
|
||||
}
|
||||
|
||||
func newOpenAICommonChatCompletionsHttpLargeLanguageModelProvider(provider OpenAIChatCompletionsLargeLanguageModelProvider) LargeLanguageModelProvider {
|
||||
return newCommonHttpLargeLanguageModelProvider(&OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: provider,
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,157 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
)
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_buildJsonRequestBody_TextualUserPrompt(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
request := &LargeLanguageModelRequest{
|
||||
SystemPrompt: "You are a helpful assistant.",
|
||||
UserPrompt: []byte("Hello, how are you?"),
|
||||
}
|
||||
|
||||
bodyBytes, err := provider.buildJsonRequestBody(core.NewNullContext(), 0, request, "test", LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
|
||||
var body map[string]interface{}
|
||||
err = json.Unmarshal(bodyBytes, &body)
|
||||
assert.Nil(t, err)
|
||||
|
||||
assert.Equal(t, "{\"messages\":[{\"content\":\"You are a helpful assistant.\",\"role\":\"system\"},{\"content\":\"Hello, how are you?\",\"role\":\"user\"}],\"model\":\"test\",\"response_format\":{\"type\":\"json_object\"},\"stream\":false}", string(bodyBytes))
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_buildJsonRequestBody_ImageUserPrompt(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
request := &LargeLanguageModelRequest{
|
||||
SystemPrompt: "What's in this image?",
|
||||
UserPrompt: []byte("fakedata"),
|
||||
UserPromptType: LARGE_LANGUAGE_MODEL_REQUEST_PROMPT_TYPE_IMAGE_URL,
|
||||
}
|
||||
|
||||
bodyBytes, err := provider.buildJsonRequestBody(core.NewNullContext(), 0, request, "test", LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
|
||||
var body map[string]interface{}
|
||||
err = json.Unmarshal(bodyBytes, &body)
|
||||
assert.Nil(t, err)
|
||||
|
||||
assert.Equal(t, "{\"messages\":[{\"content\":\"What's in this image?\",\"role\":\"system\"},{\"content\":[{\"image_url\":{\"url\":\"data:image/png;base64,ZmFrZWRhdGE=\"},\"type\":\"image_url\"}],\"role\":\"user\"}],\"model\":\"test\",\"response_format\":{\"type\":\"json_object\"},\"stream\":false}", string(bodyBytes))
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_ParseTextualResponse_ValidJsonResponse(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
response := `{
|
||||
"id": "test-123",
|
||||
"object": "chat.completion",
|
||||
"created": 1234567890,
|
||||
"model": "test",
|
||||
"usage": {
|
||||
"prompt_tokens": 13,
|
||||
"completion_tokens": 7,
|
||||
"total_tokens": 20
|
||||
},
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
"content": "This is a test response"
|
||||
}
|
||||
}
|
||||
]
|
||||
}`
|
||||
|
||||
result, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
assert.Equal(t, "This is a test response", result.Content)
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_ParseTextualResponse_EmptyResponse(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
response := `{
|
||||
"id": "test-123",
|
||||
"object": "chat.completion",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
"content": ""
|
||||
}
|
||||
}
|
||||
]
|
||||
}`
|
||||
|
||||
result, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.Nil(t, err)
|
||||
assert.Equal(t, "", result.Content)
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_ParseTextualResponse_EmptyChoices(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
response := `{
|
||||
"id": "test-123",
|
||||
"object": "chat.completion",
|
||||
"choices": []
|
||||
}`
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_ParseTextualResponse_NoChoiceContent(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
response := `{
|
||||
"id": "chatcmpl-123",
|
||||
"object": "chat.completion",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"message": {
|
||||
"role": "assistant"
|
||||
}
|
||||
}
|
||||
]
|
||||
}`
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
|
||||
func TestOpenAICommonChatCompletionsHttpLargeLanguageModelProvider_ParseTextualResponse_InvalidJson(t *testing.T) {
|
||||
provider := &OpenAICommonChatCompletionsHttpLargeLanguageModelProvider{
|
||||
provider: &OpenAILargeLanguageModelProvider{},
|
||||
}
|
||||
|
||||
response := "error"
|
||||
|
||||
_, err := provider.ParseTextualResponse(core.NewNullContext(), 0, []byte(response), LARGE_LANGUAGE_MODEL_RESPONSE_FORMAT_JSON)
|
||||
assert.EqualError(t, err, "failed to request third party api")
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
const openAICompatibleChatCompletionsPath = "chat/completions"
|
||||
|
||||
// OpenAICompatibleLargeLanguageModelProvider defines the structure of OpenAI compatible large language model provider
|
||||
type OpenAICompatibleLargeLanguageModelProvider struct {
|
||||
OpenAIChatCompletionsLargeLanguageModelProvider
|
||||
OpenAICompatibleBaseURL string
|
||||
OpenAICompatibleAPIKey string
|
||||
ReceiptImageRecognitionModelID string
|
||||
}
|
||||
|
||||
// BuildChatCompletionsHttpRequest returns the chat completions http request by OpenAI compatible provider
|
||||
func (p *OpenAICompatibleLargeLanguageModelProvider) BuildChatCompletionsHttpRequest(c core.Context, uid int64) (*http.Request, error) {
|
||||
req, err := http.NewRequest("POST", p.getFinalChatCompletionsRequestUrl(), nil)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if p.OpenAICompatibleAPIKey != "" {
|
||||
req.Header.Set("Authorization", "Bearer "+p.OpenAICompatibleAPIKey)
|
||||
}
|
||||
|
||||
return req, nil
|
||||
}
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id of OpenAI compatible provider
|
||||
func (p *OpenAICompatibleLargeLanguageModelProvider) GetReceiptImageRecognitionModelID() string {
|
||||
return p.ReceiptImageRecognitionModelID
|
||||
}
|
||||
|
||||
func (p *OpenAICompatibleLargeLanguageModelProvider) getFinalChatCompletionsRequestUrl() string {
|
||||
url := p.OpenAICompatibleBaseURL
|
||||
|
||||
if url[len(url)-1] != '/' {
|
||||
url += "/"
|
||||
}
|
||||
|
||||
url += openAICompatibleChatCompletionsPath
|
||||
return url
|
||||
}
|
||||
|
||||
// NewOpenAICompatibleLargeLanguageModelProvider creates a new OpenAI compatible large language model provider instance
|
||||
func NewOpenAICompatibleLargeLanguageModelProvider(config *settings.Config) LargeLanguageModelProvider {
|
||||
return newOpenAICommonChatCompletionsHttpLargeLanguageModelProvider(&OpenAICompatibleLargeLanguageModelProvider{
|
||||
OpenAICompatibleBaseURL: config.OpenAICompatibleBaseURL,
|
||||
OpenAICompatibleAPIKey: config.OpenAICompatibleAPIKey,
|
||||
ReceiptImageRecognitionModelID: config.OpenAICompatibleReceiptImageRecognitionModelID,
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
func TestOpenAICompatibleLargeLanguageModelProvider_GetFinalRequestUrl(t *testing.T) {
|
||||
provider := &OpenAICompatibleLargeLanguageModelProvider{
|
||||
OpenAICompatibleBaseURL: "https://api.example.com/v1/",
|
||||
}
|
||||
url := provider.getFinalChatCompletionsRequestUrl()
|
||||
assert.Equal(t, "https://api.example.com/v1/chat/completions", url)
|
||||
|
||||
provider = &OpenAICompatibleLargeLanguageModelProvider{
|
||||
OpenAICompatibleBaseURL: "https://api.example.com/v1",
|
||||
}
|
||||
url = provider.getFinalChatCompletionsRequestUrl()
|
||||
assert.Equal(t, "https://api.example.com/v1/chat/completions", url)
|
||||
|
||||
provider = &OpenAICompatibleLargeLanguageModelProvider{
|
||||
OpenAICompatibleBaseURL: "https://example.com/api",
|
||||
}
|
||||
url = provider.getFinalChatCompletionsRequestUrl()
|
||||
assert.Equal(t, "https://example.com/api/chat/completions", url)
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
// OpenAILargeLanguageModelProvider defines the structure of OpenAI large language model provider
|
||||
type OpenAILargeLanguageModelProvider struct {
|
||||
OpenAIChatCompletionsLargeLanguageModelProvider
|
||||
OpenAIAPIKey string
|
||||
ReceiptImageRecognitionModelID string
|
||||
}
|
||||
|
||||
const openAIChatCompletionsUrl = "https://api.openai.com/v1/chat/completions"
|
||||
|
||||
// BuildChatCompletionsHttpRequest returns the chat completions http request by OpenAI provider
|
||||
func (p *OpenAILargeLanguageModelProvider) BuildChatCompletionsHttpRequest(c core.Context, uid int64) (*http.Request, error) {
|
||||
req, err := http.NewRequest("POST", openAIChatCompletionsUrl, nil)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
req.Header.Set("Authorization", "Bearer "+p.OpenAIAPIKey)
|
||||
|
||||
return req, nil
|
||||
}
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id of OpenAI provider
|
||||
func (p *OpenAILargeLanguageModelProvider) GetReceiptImageRecognitionModelID() string {
|
||||
return p.ReceiptImageRecognitionModelID
|
||||
}
|
||||
|
||||
// NewOpenAILargeLanguageModelProvider creates a new OpenAI large language model provider instance
|
||||
func NewOpenAILargeLanguageModelProvider(config *settings.Config) LargeLanguageModelProvider {
|
||||
return newOpenAICommonChatCompletionsHttpLargeLanguageModelProvider(&OpenAILargeLanguageModelProvider{
|
||||
OpenAIAPIKey: config.OpenAIAPIKey,
|
||||
ReceiptImageRecognitionModelID: config.OpenAIReceiptImageRecognitionModelID,
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
package llm
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
|
||||
"github.com/mayswind/ezbookkeeping/pkg/core"
|
||||
"github.com/mayswind/ezbookkeeping/pkg/settings"
|
||||
)
|
||||
|
||||
// OpenRouterLargeLanguageModelProvider defines the structure of OpenRouter large language model provider
|
||||
type OpenRouterLargeLanguageModelProvider struct {
|
||||
OpenAIChatCompletionsLargeLanguageModelProvider
|
||||
OpenRouterAPIKey string
|
||||
ReceiptImageRecognitionModelID string
|
||||
}
|
||||
|
||||
const openRouterChatCompletionsUrl = "https://openrouter.ai/api/v1/chat/completions"
|
||||
|
||||
// BuildChatCompletionsHttpRequest returns the chat completions http request by OpenRouter provider
|
||||
func (p *OpenRouterLargeLanguageModelProvider) BuildChatCompletionsHttpRequest(c core.Context, uid int64) (*http.Request, error) {
|
||||
req, err := http.NewRequest("POST", openRouterChatCompletionsUrl, nil)
|
||||
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
req.Header.Set("Authorization", "Bearer "+p.OpenRouterAPIKey)
|
||||
req.Header.Set("HTTP-Referer", "https://ezbookkeeping.mayswind.net/")
|
||||
req.Header.Set("X-Title", "ezBookkeeping")
|
||||
|
||||
return req, nil
|
||||
}
|
||||
|
||||
// GetReceiptImageRecognitionModelID returns the receipt image recognition model id of OpenRouter provider
|
||||
func (p *OpenRouterLargeLanguageModelProvider) GetReceiptImageRecognitionModelID() string {
|
||||
return p.ReceiptImageRecognitionModelID
|
||||
}
|
||||
|
||||
// NewOpenRouterLargeLanguageModelProvider creates a new OpenRouter large language model provider instance
|
||||
func NewOpenRouterLargeLanguageModelProvider(config *settings.Config) LargeLanguageModelProvider {
|
||||
return newOpenAICommonChatCompletionsHttpLargeLanguageModelProvider(&OpenRouterLargeLanguageModelProvider{
|
||||
OpenRouterAPIKey: config.OpenRouterAPIKey,
|
||||
ReceiptImageRecognitionModelID: config.OpenRouterReceiptImageRecognitionModelID,
|
||||
})
|
||||
}
|
||||
Reference in New Issue
Block a user