add model mapping for embeddings #21
Open
Conversation
This file contains hidden or 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
jordanstephens
approved these changes
Jun 11, 2025
| @@ -82,7 +47,7 @@ def get_proxy_target(model, path): | |||
| else: | |||
| return f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/{model}:rawPredict" | |||
|
|
|||
| def get_headers(model, request, path): | |||
| def get_header(model, request, path): | |||
There was a problem hiding this comment.
Suggested change
| def get_header(model, request, path): | |
| def get_headers(model, request, path): |
| @@ -159,7 +127,7 @@ async def handle_proxy(request: Request, path: str): | |||
| conversion_target = "anthropic" | |||
|
|
|||
| # Build safe target URL | |||
| target_url, request_headers = get_headers(model, request, path) | |||
| target_url, request_headers = get_header(model, request, path) | |||
There was a problem hiding this comment.
Suggested change
| target_url, request_headers = get_header(model, request, path) | |
| target_url, request_headers = get_headers(model, request, path) |
Comment on lines
+46
to
+58
| vertex_request = { | ||
| "instances": [] | ||
| } | ||
|
|
||
| msg_input = request.get("input") | ||
| if type(msg_input) is str: | ||
| vertex_request["instances"] = [{ | ||
| "content": f"{msg_input}" | ||
| }] | ||
| elif type(msg_input) is list: | ||
| vertex_request["instances"] = [{"content": f"{str(item)}"} for item in msg_input] | ||
|
|
||
| return vertex_request |
There was a problem hiding this comment.
I think we can tighten this up a bit. What do you think of this?
Suggested change
| vertex_request = { | |
| "instances": [] | |
| } | |
| msg_input = request.get("input") | |
| if type(msg_input) is str: | |
| vertex_request["instances"] = [{ | |
| "content": f"{msg_input}" | |
| }] | |
| elif type(msg_input) is list: | |
| vertex_request["instances"] = [{"content": f"{str(item)}"} for item in msg_input] | |
| return vertex_request | |
| inputs = request.get("input", []) | |
| if not isinstance(inputs, list): | |
| inputs = [inputs] | |
| return { | |
| "instances": [{"content": str(content)} for content in inputs] | |
| } |
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.
Description of changes:
Add GCP embeddings. Converts OpenAI embeddings request to a vertex embeddings to make call to model. Response is conversely converted from vertex response to OpenAI embeddings response.
The previous vertex.py was changed to chat.py (parallels how AWS does it). Minimal changes to AWS code to ensure we don't have major issues taking upstream changes.