Feat/llm config (#724)

* feature: Add LlmConfig to easily configure and pass LLM configs to different strategies

* pulled in next branch and resolved conflicts

* feat: Add gemini and deepseek providers. Make ignore_cache in llm content filter to true by default to avoid confusions

* Refactor: Update LlmConfig in LLMExtractionStrategy class and deprecate old params

* updated tests, docs and readme
This commit is contained in:
Aravind
2025-02-21 13:11:37 +05:30
committed by GitHub
parent 3cb28875c3
commit 2af958e12c
25 changed files with 420 additions and 240 deletions

View File

@@ -21,6 +21,12 @@ PROVIDER_MODELS = {
"anthropic/claude-3-opus-20240229": os.getenv("ANTHROPIC_API_KEY"),
"anthropic/claude-3-sonnet-20240229": os.getenv("ANTHROPIC_API_KEY"),
"anthropic/claude-3-5-sonnet-20240620": os.getenv("ANTHROPIC_API_KEY"),
"gemini/gemini-pro": os.getenv("GEMINI_API_KEY"),
'gemini/gemini-1.5-pro': os.getenv("GEMINI_API_KEY"),
'gemini/gemini-2.0-flash': os.getenv("GEMINI_API_KEY"),
'gemini/gemini-2.0-flash-exp': os.getenv("GEMINI_API_KEY"),
'gemini/gemini-2.0-flash-lite-preview-02-05': os.getenv("GEMINI_API_KEY"),
"deepseek/deepseek-chat": os.getenv("DEEPSEEK_API_KEY"),
}
# Chunk token threshold