docs(models): document litellm-sdk embeddings provider#1336
Merged
nicoloboschi merged 2 commits intoApr 30, 2026
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
litellm-sdkis a real, functional embeddings provider (registered viaembeddings_litellm_sdk_*config inhindsight-api-slim/hindsight_api/config.py, instantiated by theLiteLLMSDKEmbeddingsclass atembeddings.py:753, and listed in the unknown-provider error message:"Supported: 'local', 'tei', 'openai', 'cohere', 'google', 'litellm', 'litellm-sdk'"atembeddings.py:1209). It also gets continued investment — #1320 (merged a few hours ago) wiredallowed_openai_params=["dimensions"]soHINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_OUTPUT_DIMENSIONSactually works for OpenAI-compatible custom models.But the embedding providers table at
docs/developer/models.mdxonly lists six providers (local/openai/cohere/google/tei/litellm) —litellm-sdkis missing. The cross-encoder providers table on the same page already documents it (| litellm-sdk | LiteLLM SDK (direct API, no proxy) | Multi-provider, simpler setup |), so users reading the embeddings section can't tell the SDK path is supported.What's in the PR
hindsight-docs/docs/developer/models.mdx(+5 LOC): one new row in the embedding providers table mirroring the cross-encoder description; one new# LiteLLM SDK (direct, no proxy)stanza in the Configuration Examples block (mirrors the existing# LiteLLM proxystanza style).skills/hindsight-docs/references/developer/models.md(+5 LOC): byte-for-byte mirror.Source of truth
LiteLLMSDKEmbeddings.provider_namereturns"litellm-sdk"(embeddings.py:802); factory dispatchesprovider == "litellm-sdk"(embeddings.py:1173).HINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_API_KEYandHINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_MODELdefined atconfig.py:223-224. API key is required (factory raisesValueErrorif unset,embeddings.py:1175-1178).openai/text-embedding-3-smallfollows the LiteLLM provider-prefix convention used throughout the existing docs (and is the path fix(embeddings): add allowed_openai_params for OpenAI-compatible embedding dimensions #1320 just made fully functional).Pure docs, no behavior change.