mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
3671829e39
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 12s
* refactor: initial commit moving watsonx_text to base_llm_http_handler + clarifying new provider directory structure * refactor(watsonx/completion/handler.py): move to using base llm http handler removes 'requests' library usage * fix(watsonx_text/transformation.py): fix result transformation migrates to transformation.py, for usage with base llm http handler * fix(streaming_handler.py): migrate watsonx streaming to transformation.py ensures streaming works with base llm http handler * fix(streaming_handler.py): fix streaming linting errors and remove watsonx conditional logic * fix(watsonx/): fix chat route post completion route refactor * refactor(watsonx/embed): refactor watsonx to use base llm http handler for embedding calls as well * refactor(base.py): remove requests library usage from litellm * build(pyproject.toml): remove requests library usage * fix: fix linting errors * fix: fix linting errors * fix(types/utils.py): fix validation errors for modelresponsestream * fix(replicate/handler.py): fix linting errors * fix(litellm_logging.py): handle modelresponsestream object * fix(streaming_handler.py): fix modelresponsestream args * fix: remove unused imports * test: fix test * fix: fix test * test: fix test * test: fix tests * test: fix test * test: fix patch target * test: fix test
809 B
809 B
Directory Structure
When adding a new provider, you need to create a directory for the provider that follows the following structure:
litellm/llms/
└── provider_name/
├── completion/ # use when endpoint is equivalent to openai's `/v1/completions`
│ ├── handler.py
│ └── transformation.py
├── chat/ # use when endpoint is equivalent to openai's `/v1/chat/completions`
│ ├── handler.py
│ └── transformation.py
├── embed/ # use when endpoint is equivalent to openai's `/v1/embeddings`
│ ├── handler.py
│ └── transformation.py
└── rerank/ # use when endpoint is equivalent to cohere's `/rerank` endpoint.
├── handler.py
└── transformation.py