refactor(forge/llm): Create BaseOpenAIProvider -> deduplicate GroqProvider & OpenAIProvider
#7178
Conversation
This file contains 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
…deduplicate `GroqProvider` & `OpenAIProvider` - Add `_BaseOpenAIProvider`, `BaseOpenAIChatProvider`, and `BaseOpenAIEmbeddingProvider` - (Re)move as much code as possible from `GroqProvider` and `OpenAIProvider` Also: - Rename `get_available_models()` to `get_available_chat_models()` on `BaseChatModelProvider` - Add `get_available_models()` to `BaseModelProvider` - Add `get_available_embedding_models()` to `BaseEmbeddingModelProvider` - Move common `fix_failed_parse_tries` config attribute into base `ModelProviderConfiguration`
Pwuts
requested review from
Torantulino and
Bentlybro
and removed request for
a team
✅ Deploy Preview for auto-gpt-docs canceled.
|
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #7178 +/- ##
==========================================
+ Coverage 33.75% 42.70% +8.95%
==========================================
Files 22 83 +61
Lines 1893 4826 +2933
Branches 330 657 +327
==========================================
+ Hits 639 2061 +1422
- Misses 1240 2673 +1433
- Partials 14 92 +78
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
Pwuts
changed the title
BaseOpenAI(Chat|Embedding)Provider and deduplicate GroqProvider & OpenAIProviderBaseOpenAIProvider and deduplicate GroqProvider & OpenAIProvider
Pwuts
changed the title
BaseOpenAIProvider and deduplicate GroqProvider & OpenAIProviderBaseOpenAIProvider -> deduplicate GroqProvider & OpenAIProvider
ntindle
reviewed
May 31, 2024
ntindle
approved these changes
May 31, 2024
Pwuts
deleted the
reinier/open-1100-abstract-openaiprovider-groqprovider-to-a-common
branch
9 tasks
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.
It seems to be a trend for new LLM providers to mimic the OpenAI API. The same goes for Llamafile. We can leverage this and create a common base class that implements most of the functionality for providers with OpenAI-like interfaces. This has the additional benefit of increasing maintainability and making it easier to add support for more such providers in the future.
This PR also paves the way for a clean integration of #7091.
Changes
_BaseOpenAIProvider,BaseOpenAIChatProvider, andBaseOpenAIEmbeddingProviderGroqProviderandOpenAIProviderAlso:
get_available_models()toget_available_chat_models()onBaseChatModelProviderget_available_models()toBaseModelProviderget_available_embedding_models()toBaseEmbeddingModelProviderfix_failed_parse_triesconfig attribute into baseModelProviderConfiguration