community: update documentation and model IDs for FriendliAI provider #28984
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
Remove unused models, fix streaming, update docs Remove llama-2-13b-chat, mixtral-8x7b-instruct-v0-1; fix llm friendli streaming; update docs examples Delete duplicate documents Remove llama-2-13b-chat, mixtral-8x7b-instruct-v0-1; fix llm friendli streaming; update docs examples Add example fix: update model version to meta-llama-3.1-8b-instruct in Friendli integration fix: simplify ValueError messages in Friendli model parameters refactor: streamline formatting in _stream_response_to_generation_chunk test: Refactor async stream test for Friendli to use mock choices test: Update Friendli async stream test to use correct mock choices test: Update Friendli stream tests to use choices for assertions test: Update Friendli async stream test to use AsyncMock for better async handling test: Update Friendli stream tests to use mock choices for consistency test: Update Friendli stream tests to assert chunk values directly for clarity test: Refactor Friendli stream response handling and update async test mocks refactor: Change type hint for stream_response parameter to Any for flexibility docs: Update Friendli notebook to correct execution counts and links
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
ccurme
approved these changes
Jan 2, 2025
Comment on lines
+27
to
+30
| # generation_info=dict( | ||
| # finish_reason=stream_response.choices[0].get("finish_reason", None), | ||
| # logprobs=stream_response.choices[0].get("logprobs", None), | ||
| # ), |
Collaborator
There was a problem hiding this comment.
Suggested change
| # generation_info=dict( | |
| # finish_reason=stream_response.choices[0].get("finish_reason", None), | |
| # logprobs=stream_response.choices[0].get("logprobs", None), | |
| # ), |
| ], | ||
| "source": ["llm.generate([\"Tell me a joke.\", \"Tell me a joke.\"])"] | ||
| "source": [ | ||
| "llm.generate([\"Tell me a joke.\", \"Tell me a joke.\"])" |
Collaborator
There was a problem hiding this comment.
Don't think we need to show .generate
|
|
||
| Sign in to [Friendli Suite](https://suite.friendli.ai/) to create a Personal Access Token, | ||
| and set it as the `FRIENDLI_TOKEN` environment variable. | ||
| and set it as the `FRIENDLI_TOKEN` environment variabzle. |
Collaborator
There was a problem hiding this comment.
Suggested change
| and set it as the `FRIENDLI_TOKEN` environment variabzle. | |
| and set it as the `FRIENDLI_TOKEN` environment variable. |
Collaborator
|
Would you be interested in publishing an OSS integration package (e.g., https://python.langchain.com/docs/contributing/how_to/integrations/ We are encouraging contributors of LangChain integrations to go this route. This way we don't have to be in the loop for reviews, you're able to properly integration test the model, and you have control over versioning. Docs would continue to be maintained in the Let me know what you think! |
pprados
pushed a commit
to pprados/langchain
that referenced
this pull request
Jan 3, 2025
…langchain-ai#28984) ### Description - In the example, remove `llama-2-13b-chat`, `mixtral-8x7b-instruct-v0-1`. - Fix llm friendli streaming implementation. - Update examples in documentation and remove duplicates. ### Issue N/A ### Dependencies None ### Twitter handle `@friendliai`
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Description
llama-2-13b-chat,mixtral-8x7b-instruct-v0-1.Issue
N/A
Dependencies
None
Twitter handle
@friendliai