gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cherry-pick f24a2616

Browse source
This commit is contained in:
Raphaël MANSUY 2025-12-04 19:18:38 +08:00
parent 96715f92e1
commit 114b400905
1 changed files with 40 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
lightrag/api/routers/query_routes.py
View file

@ -75,6 +75,16 @@ class QueryRequest(BaseModel):
ge=1,
)
hl_keywords: list[str] = Field(
default_factory=list,
description="List of high-level keywords to prioritize in retrieval. Leave empty to use the LLM to generate the keywords.",
)
ll_keywords: list[str] = Field(
default_factory=list,
description="List of low-level keywords to refine retrieval focus. Leave empty to use the LLM to generate the keywords.",
)
conversation_history: Optional[List[Dict[str, Any]]] = Field(
default=None,
description="Stores past conversation history to maintain context. Format: [{'role': 'user/assistant', 'content': 'message'}].",
@ -357,6 +367,16 @@ def create_query_routes(rag, api_key: Optional[str] = None, top_k: int = 60, rag
}
```
Bypass initial LLM call by providing high-level and low-level keywords:
```json
{
"query": "What is Retrieval-Augmented-Generation?",
"hl_keywords": ["machine learning", "information retrieval", "natural language processing"],
"ll_keywords": ["retrieval augmented generation", "RAG", "knowledge base"],
"mode": "mix"
}
```
Advanced query with references:
```json
{
@ -574,6 +594,16 @@ def create_query_routes(rag, api_key: Optional[str] = None, top_k: int = 60, rag
}
```
Bypass initial LLM call by providing high-level and low-level keywords:
```json
{
"query": "What is Retrieval-Augmented-Generation?",
"hl_keywords": ["machine learning", "information retrieval", "natural language processing"],
"ll_keywords": ["retrieval augmented generation", "RAG", "knowledge base"],
"mode": "mix"
}
```
Complete response query:
```json
{
@ -1063,6 +1093,16 @@ def create_query_routes(rag, api_key: Optional[str] = None, top_k: int = 60, rag
}
```
Bypass initial LLM call by providing high-level and low-level keywords:
```json
{
"query": "What is Retrieval-Augmented-Generation?",
"hl_keywords": ["machine learning", "information retrieval", "natural language processing"],
"ll_keywords": ["retrieval augmented generation", "RAG", "knowledge base"],
"mode": "mix"
}
```
**Response Analysis:**
- **Empty arrays**: Normal for certain modes (e.g., naive mode has no entities/relationships)
- **Processing info**: Shows retrieval statistics and token usage