Add endpoint parameter to TextEmbeddingsInference

[thommann]

… to allow overwriting the default endpoint "/embed"

Description

Allow for a custom endpoint in the TextEmbeddingInference class. This allows to overwrite the default "/embed" endpoint. This is needed to use the "/embedding" endpoint of services like the llama.cpp server.

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

• New feature (non-breaking change which adds functionality)

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• My changes generate no new warnings
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

This looks pretty good to me. Any reason its a draft?

[thommann]

This looks pretty good to me. Any reason its a draft?

I tried to use it with a llama.cpp server to host the embedding model. The problem is, that it is not only the endpoint that is different, but also the format of the response body. Both are hard-coded in the TextEmbeddingInference.