[ENH] Add Cloudflare Worker AI Embedding Function #4389
Conversation
Reviewer ChecklistPlease leverage this checklist to ensure your code review is thorough before approving Testing, Bugs, Errors, Logs, Documentation
System Compatibility
Quality
|
jairad26
changed the base branch from
jai/python-close-clients
to
graphite-base/4389
jairad26
force-pushed
the
jai/cloudflare-workers-ef
branch
from
fe8bef0 to
08d65ed
Compare
jairad26
force-pushed
the
graphite-base/4389
branch
from
c14ea0c to
7d01a2b
Compare
| if not self.api_key: | ||
| raise ValueError(f"The {api_key_env_var} environment variable is not set.") | ||
|
|
||
| self._api_url = f"https://api.cloudflare.com/client/v4/accounts/{self.account_id}/ai/run/{self.model_name}" |
There was a problem hiding this comment.
nit move base url to a const at top of file
| return "cloudflare_workers_ai" | ||
|
|
||
| def default_space(self) -> Space: | ||
| return "l2" |
There was a problem hiding this comment.
is this the best default space?
There was a problem hiding this comment.
https://huggingface.co/BAAI/bge-large-en-v1.5
I think the BAAI models being used prefer others https://developers.cloudflare.com/workers-ai/models/
There was a problem hiding this comment.
yea youre right, they use cosine, updated
| api_key_env_var: str = "CHROMA_CLOUDFLARE_API_KEY", | ||
| ): | ||
| """ | ||
| Initialize the CloudflareWorkersAIEmbeddingFunction. |
There was a problem hiding this comment.
might be useful to link to CF docs - https://developers.cloudflare.com/workers-ai/models/
| if not self.api_key: | ||
| raise ValueError(f"The {api_key_env_var} environment variable is not set.") | ||
|
|
||
| self._api_url = f"https://api.cloudflare.com/client/v4/accounts/{self.account_id}/ai/run/{self.model_name}" |
There was a problem hiding this comment.
Cloudflare also supports AI Gateway, which allows for higher limits and more control - https://developers.cloudflare.com/ai-gateway/
Might be a good idea to also include that for completeness. The difference between the two is the endpoint composition.
There was a problem hiding this comment.
thanks, added a gateway_id
jairad26
force-pushed
the
jai/cloudflare-workers-ef
branch
from
08d65ed to
3ce0000
Compare
Description of changes
This PR adds support for cloudflare worker embedding function across both python and typescript, adds docs, and schema validation
Test plan
How are these changes tested?
pytestfor python,yarn testfor js,cargo testfor rustDocumentation Changes
Are all docstrings for user-facing APIs updated if required? Do we need to make documentation changes in the docs section?