feat: add gemini vertex model provider #297
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
iwilltry42
force-pushed
the
feat/gemini-vertex-model-provider
branch
from
b1d1b1f to
9b9764a
Compare
iwilltry42
requested review from
thedadams,
njhale,
sanjay920,
StrongMonkey and
g-linville
iwilltry42
force-pushed
the
feat/gemini-vertex-model-provider
branch
from
9b9764a to
cfbf03f
Compare
|
My concern with this is that it is not I noticed that there is a Go package: https://github.com/googleapis/go-genai In your opinion, would this work for us? |
|
Back to draft for the rewrite to Go... |
iwilltry42
force-pushed
the
feat/gemini-vertex-model-provider
branch
2 times, most recently
from
98cb57c to
69fd5cf
Compare
|
Go Rewrite is done, but I'll continue implementing the embeddings API as well |
|
With the Go rewrite, I also the /embeddings endpoint (needed a custom implementation as it's not part of their SDK and I couldn't get it working with what they have there so far... I re-used a bunch of code from knowledge, so it's fine). |
iwilltry42
force-pushed
the
feat/gemini-vertex-model-provider
branch
from
c8d48dc to
0fa890a
Compare
thedadams
requested changes
Jan 10, 2025
| } | ||
|
|
||
| func configure(ctx context.Context) (*genai.Client, error) { | ||
|
|
| if err := validate(ctx); err != nil { | ||
| fmt.Printf("{\"error\": \"%s\"}\n", err) | ||
| } | ||
| os.Exit(1) |
There was a problem hiding this comment.
We probably don't want to always exit 1 for `validate.
| } | ||
|
|
||
| func Run(client *genai.Client, port string) error { | ||
|
|
Comment on lines
+43
to
+45
| mux.HandleFunc("/v1/models", s.listModels) | ||
| mux.HandleFunc("/v1/chat/completions", s.chatCompletions) | ||
| mux.HandleFunc("/v1/embeddings", s.embeddings) |
There was a problem hiding this comment.
Suggested change
| mux.HandleFunc("/v1/models", s.listModels) | |
| mux.HandleFunc("/v1/chat/completions", s.chatCompletions) | |
| mux.HandleFunc("/v1/embeddings", s.embeddings) | |
| mux.HandleFunc("GET /v1/models", s.listModels) | |
| mux.HandleFunc("POST /v1/chat/completions", s.chatCompletions) | |
| mux.HandleFunc("POST /v1/embeddings", s.embeddings) |
| http.Error(w, err.Error(), http.StatusInternalServerError) | ||
| return | ||
| } | ||
|
|
| return choices, nil | ||
| } | ||
|
|
||
| func mapToOpenAIChoice(candidates []*genai.Candidate) ([]openai.ChatCompletionChoice, error) { |
There was a problem hiding this comment.
Same nits on this function
| } | ||
|
|
||
| func mapMessagesFromOpenAI(messages []openai.ChatCompletionMessage) ([]*genai.Content, error) { | ||
|
|
|
|
||
| // embeddings - not (yet) provided by the Google GenAI package | ||
| func (s *server) embeddings(w http.ResponseWriter, r *http.Request) { | ||
|
|
| defer resp.Body.Close() | ||
|
|
||
| if resp.StatusCode != http.StatusOK { | ||
| http.Error(w, fmt.Sprintf("unexpected status code: %d", resp.StatusCode), http.StatusInternalServerError) |
There was a problem hiding this comment.
Does this make sense?
Suggested change
| http.Error(w, fmt.Sprintf("unexpected status code: %d", resp.StatusCode), http.StatusInternalServerError) | |
| http.Error(w, fmt.Sprintf("unexpected status code: %d", resp.StatusCode), resp.StatusCode) |
Comment on lines
+619
to
+630
| body, err := io.ReadAll(resp.Body) | ||
| if err != nil { | ||
| http.Error(w, fmt.Sprintf("couldn't read response body: %v", err), http.StatusInternalServerError) | ||
| return | ||
| } | ||
|
|
||
| var embeddingResponse vertexEmbeddingResponse | ||
| err = json.Unmarshal(body, &embeddingResponse) | ||
| if err != nil { | ||
| http.Error(w, fmt.Sprintf("couldn't unmarshal response body: %v", err), http.StatusInternalServerError) | ||
| return | ||
| } |
There was a problem hiding this comment.
Can we combine these with json.NewDecoder(resp.Body).Decode(&embeddingResponse)?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Already implements the /validate endpoint from obot-platform/obot#1019
Ref: obot-platform/obot#872