Add LiteLLM chat and embedding model providers. #2026
Closed
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
|
Just adding a note here that this PR should close #1575. |
There was a problem hiding this comment.
Pull Request Overview
This pull request adds LiteLLM as a new provider for both chat and embedding models in GraphRAG, significantly expanding the library's model support to include many additional providers through LiteLLM's unified interface.
- Implements LiteLLM chat and embedding model classes with comprehensive request wrappers
- Adds robust retry mechanisms with multiple strategies (native, exponential backoff, random wait, incremental wait)
- Implements static rate limiting with RPM/TPM controls and threading support
Reviewed Changes
Copilot reviewed 32 out of 33 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| pyproject.toml | Adds litellm dependency to the project |
| graphrag/config/enums.py | Adds new LitellmChat and LitellmEmbedding model types |
| graphrag/config/models/language_model_config.py | Extends configuration to support LiteLLM with model_provider field and validation |
| graphrag/config/defaults.py | Adds model_provider default configuration |
| graphrag/language_model/factory.py | Registers new LiteLLM model types in the factory |
| graphrag/language_model/providers/litellm/ | Complete LiteLLM implementation including chat/embedding models, retry services, rate limiting, and request wrappers |
| tests/unit/litellm_services/ | Comprehensive test suite covering retry mechanisms and rate limiting functionality |
| dictionary.txt | Adds litellm to the project dictionary |
| .semversioner/next-release/ | Marks this as a minor version release |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
graphrag/language_model/providers/litellm/services/rate_limiter/rate_limiter.py
Outdated
Show resolved
Hide resolved
graphrag/language_model/providers/litellm/request_wrappers/with_retries.py
Outdated
Show resolved
Hide resolved
graphrag/language_model/providers/litellm/request_wrappers/with_retries.py
Outdated
Show resolved
Hide resolved
andresmor-ms
reviewed
Sep 8, 2025
Comment on lines
+57
to
+68
| if model_config.api_base: | ||
| base_args["api_base"] = model_config.api_base | ||
| if model_config.api_version: | ||
| base_args["api_version"] = model_config.api_version | ||
| if model_config.api_key: | ||
| base_args["api_key"] = model_config.api_key | ||
| if model_config.organization: | ||
| base_args["organization"] = model_config.organization | ||
| if model_config.proxy: | ||
| base_args["proxy"] = model_config.proxy | ||
| if model_config.audience: | ||
| base_args["audience"] = model_config.audience |
There was a problem hiding this comment.
could this be replaced by something like:
base_args.update({
"api_base": model_config.api_base,
...
})?
|
Closing in favor of #2051 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Add LiteLLM chat and embedding model providers.