Spaces:
Sleeping
Sleeping
File size: 9,763 Bytes
f871fed | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 | import json
from typing import AsyncGenerator
from fastapi import APIRouter, HTTPException
from fastapi.responses import StreamingResponse
from loguru import logger
from api.models import AskRequest, AskResponse, DirectAskRequest, SearchRequest, SearchResponse
from open_notebook.domain.models import Model, model_manager
from open_notebook.domain.notebook import text_search, vector_search
from open_notebook.exceptions import DatabaseOperationError, InvalidInputError
from open_notebook.graphs.ask import graph as ask_graph
router = APIRouter()
@router.post("/search", response_model=SearchResponse)
async def search_knowledge_base(search_request: SearchRequest):
"""Search the knowledge base using text or vector search."""
try:
if search_request.type == "vector":
# Check if embedding model is available for vector search
if not await model_manager.get_embedding_model():
raise HTTPException(
status_code=400,
detail="Vector search requires an embedding model. Please configure one in the Models section.",
)
results = await vector_search(
keyword=search_request.query,
results=search_request.limit,
source=search_request.search_sources,
note=search_request.search_notes,
minimum_score=search_request.minimum_score,
)
else:
# Text search
results = await text_search(
keyword=search_request.query,
results=search_request.limit,
source=search_request.search_sources,
note=search_request.search_notes,
)
return SearchResponse(
results=results or [],
total_count=len(results) if results else 0,
search_type=search_request.type,
)
except InvalidInputError as e:
raise HTTPException(status_code=400, detail=str(e))
except DatabaseOperationError as e:
logger.error(f"Database error during search: {str(e)}")
raise HTTPException(status_code=500, detail=f"Search failed: {str(e)}")
except Exception as e:
logger.error(f"Unexpected error during search: {str(e)}")
raise HTTPException(status_code=500, detail=f"Search failed: {str(e)}")
async def stream_ask_response(
question: str, strategy_model: Model, answer_model: Model, final_answer_model: Model
) -> AsyncGenerator[str, None]:
"""Stream the ask response as Server-Sent Events."""
try:
final_answer = None
async for chunk in ask_graph.astream(
input=dict(question=question), # type: ignore[arg-type]
config=dict(
configurable=dict(
strategy_model=strategy_model.id,
answer_model=answer_model.id,
final_answer_model=final_answer_model.id,
)
),
stream_mode="updates",
):
if "agent" in chunk:
strategy_data = {
"type": "strategy",
"reasoning": chunk["agent"]["strategy"].reasoning,
"searches": [
{"term": search.term, "instructions": search.instructions}
for search in chunk["agent"]["strategy"].searches
],
}
yield f"data: {json.dumps(strategy_data)}\n\n"
elif "provide_answer" in chunk:
for answer in chunk["provide_answer"]["answers"]:
answer_data = {"type": "answer", "content": answer}
yield f"data: {json.dumps(answer_data)}\n\n"
elif "write_final_answer" in chunk:
final_answer = chunk["write_final_answer"]["final_answer"]
final_data = {"type": "final_answer", "content": final_answer}
yield f"data: {json.dumps(final_data)}\n\n"
# Send completion signal
completion_data = {"type": "complete", "final_answer": final_answer}
yield f"data: {json.dumps(completion_data)}\n\n"
except Exception as e:
logger.error(f"Error in ask streaming: {str(e)}")
error_data = {"type": "error", "message": str(e)}
yield f"data: {json.dumps(error_data)}\n\n"
@router.post("/search/ask")
async def ask_knowledge_base(ask_request: AskRequest):
"""Ask the knowledge base a question using AI models."""
try:
# Validate models exist
strategy_model = await Model.get(ask_request.strategy_model)
answer_model = await Model.get(ask_request.answer_model)
final_answer_model = await Model.get(ask_request.final_answer_model)
if not strategy_model:
raise HTTPException(
status_code=400,
detail=f"Strategy model {ask_request.strategy_model} not found",
)
if not answer_model:
raise HTTPException(
status_code=400,
detail=f"Answer model {ask_request.answer_model} not found",
)
if not final_answer_model:
raise HTTPException(
status_code=400,
detail=f"Final answer model {ask_request.final_answer_model} not found",
)
# Check if embedding model is available
if not await model_manager.get_embedding_model():
raise HTTPException(
status_code=400,
detail="Ask feature requires an embedding model. Please configure one in the Models section.",
)
# For streaming response
return StreamingResponse(
stream_ask_response(
ask_request.question, strategy_model, answer_model, final_answer_model
),
media_type="text/plain",
)
except HTTPException:
raise
except Exception as e:
logger.error(f"Error in ask endpoint: {str(e)}")
raise HTTPException(status_code=500, detail=f"Ask operation failed: {str(e)}")
@router.post("/search/ask/simple", response_model=AskResponse)
async def ask_knowledge_base_simple(ask_request: AskRequest):
"""Ask the knowledge base a question and return a simple response (non-streaming)."""
try:
# Validate models exist
strategy_model = await Model.get(ask_request.strategy_model)
answer_model = await Model.get(ask_request.answer_model)
final_answer_model = await Model.get(ask_request.final_answer_model)
if not strategy_model:
raise HTTPException(
status_code=400,
detail=f"Strategy model {ask_request.strategy_model} not found",
)
if not answer_model:
raise HTTPException(
status_code=400,
detail=f"Answer model {ask_request.answer_model} not found",
)
if not final_answer_model:
raise HTTPException(
status_code=400,
detail=f"Final answer model {ask_request.final_answer_model} not found",
)
# Check if embedding model is available
if not await model_manager.get_embedding_model():
raise HTTPException(
status_code=400,
detail="Ask feature requires an embedding model. Please configure one in the Models section.",
)
# Run the ask graph and get final result
final_answer = None
async for chunk in ask_graph.astream(
input=dict(question=ask_request.question), # type: ignore[arg-type]
config=dict(
configurable=dict(
strategy_model=strategy_model.id,
answer_model=answer_model.id,
final_answer_model=final_answer_model.id,
)
),
stream_mode="updates",
):
if "write_final_answer" in chunk:
final_answer = chunk["write_final_answer"]["final_answer"]
if not final_answer:
raise HTTPException(status_code=500, detail="No answer generated")
return AskResponse(answer=final_answer, question=ask_request.question)
except HTTPException:
raise
except Exception as e:
logger.error(f"Error in ask simple endpoint: {str(e)}")
raise HTTPException(status_code=500, detail=f"Ask operation failed: {str(e)}")
@router.post("/search/ask/direct", response_model=AskResponse)
async def ask_ai_direct(request: DirectAskRequest):
"""
Ask AI directly without RAG/knowledge retrieval.
This uses the LLM's general knowledge to answer questions.
"""
try:
from open_notebook.graphs.utils import provision_langchain_model
# Use the default chat model for direct questions
model = await provision_langchain_model(
content=request.question,
model_id=request.model_id,
default_type="chat",
max_tokens=2048
)
# Create prompt for direct AI response
prompt = f"""You are a helpful AI assistant. Answer the following question directly using your knowledge.
Be clear, concise, and informative.
Question: {request.question}
Answer:"""
response = await model.ainvoke(prompt)
answer = response.content if hasattr(response, 'content') else str(response)
return AskResponse(answer=answer, question=request.question)
except Exception as e:
logger.error(f"Error in direct AI endpoint: {str(e)}")
raise HTTPException(status_code=500, detail=f"Direct AI query failed: {str(e)}")
|