feat: enhance RAG functionality with context character limits, query rewriting options, and improved timeout settings
Build and Release / release (push) Successful in 1m31s
Build and Release / release (push) Successful in 1m31s
This commit is contained in:
@@ -133,15 +133,20 @@ history-api/
|
||||
GOOGLE_AI_EMBEDDING_MODEL=
|
||||
|
||||
OPEN_ROUTER_API=
|
||||
OPEN_ROUTER_MODEL=
|
||||
OPEN_ROUTER_FALLBACK_MODEL=qwen/qwen3-30b-a3b-instruct-2507
|
||||
OPEN_ROUTER_MODEL=qwen/qwen3-30b-a3b-instruct-2507
|
||||
OPEN_ROUTER_FALLBACK_MODEL=google/gemini-2.5-flash-lite
|
||||
OPEN_ROUTER_EMBEDDING_MODEL=
|
||||
|
||||
RAG_LLM_TIMEOUT_SECONDS=20
|
||||
RAG_QUERY_REWRITE_ENABLED=true
|
||||
RAG_QUERY_REWRITE_MODEL=google/gemini-2.5-flash-lite
|
||||
RAG_QUERY_REWRITE_TIMEOUT_SECONDS=5
|
||||
RAG_QUERY_REWRITE_MAX_TOKENS=96
|
||||
RAG_REWRITE_HISTORY_TURNS=3
|
||||
RAG_RETRIEVAL_CANDIDATES=30
|
||||
RAG_CONTEXT_TOP_N=8
|
||||
RAG_GENERATION_MAX_RETRIES=2
|
||||
RAG_CONTEXT_TOP_N=5
|
||||
RAG_CONTEXT_MAX_CHARS=8000
|
||||
RAG_GENERATION_MAX_RETRIES=1
|
||||
RAG_GENERATION_RETRY_DELAY_MS=500
|
||||
RAG_RERANK_ENABLED=true
|
||||
RAG_RERANK_MODEL=cohere/rerank-4-pro
|
||||
|
||||
Reference in New Issue
Block a user