File size: 8,195 Bytes
d9e3edb | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 | # import os
# import sys
# sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# import json
# from pydantic import ValidationError
# from src.assistants.assistant_v1 import gemini_rag_assistant
# from src.utils.knowledge_base import AgenticRAG
# async def get_response(query=True, is_uploaded=False):
# rag = AgenticRAG(query_value=query, is_uploaded=is_uploaded)
# # query = input("Enter your query: ")
# context = rag.query(query_text=query, n_results=10)
# print("\nQuery Results:")
# print(json.dumps(context, indent=2))
# try:
# response = await gemini_rag_assistant.get_response(
# message=query, context_data=context
# )
# print("\nAssistant Response:")
# print(response)
# return {"response": response, "context": context}
# except ValidationError as e:
# print("Validation Error:", e)
# return {
# "source_id": "validation_error",
# "content": str(e),
# }
# except Exception as e:
# print("Internal Server Error:", e)
# return {
# "source_id": "internal_error",
# "content": "Internal Server Error",
# }
# async def main():
# rag = AgenticRAG(query_value=True)
# # while True:
# query = input("Enter your query: ")
# results = rag.query(query_text=query, n_results=10)
# print("\nQuery Results:")
# print(json.dumps(results, indent=2))
# try:
# print("gemini start generating answer")
# response = await gemini_rag_assistant.get_response(
# message=query, context_data=results
# )
# print("\nAssistant Response:")
# print(response)
# except ValidationError as e:
# print("Validation Error:", e)
# return {
# "source_id": "validation_error",
# "content": str(e),
# }
# except Exception as e:
# print("Internal Server Error:", e)
# return {
# "source_id": "internal_error",
# "content": "Internal Server Error",
# }
# if __name__ == "__main__":
# import asyncio
# asyncio.run(main())
import json
import os
import traceback
import google.generativeai as genai
from dotenv import load_dotenv
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel, ValidationError
from agents_rag.crew import get_crew_response
from assistants.assistant_v1 import gemini_rag_assistant
from utils.knowledge_base import AgenticRAG
from utils.vectorDB import VectorStore
load_dotenv()
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
genai.configure(api_key=GEMINI_API_KEY)
# Initialize FastAPI app
app = FastAPI(title="Gemini RAG Assistant API", version="1.0.0")
# Pydantic model for request body
class QueryRequest(BaseModel):
query: str
is_uploaded: bool = False
url: str
# Pydantic model for response
class QueryResponse(BaseModel):
response: str
context: dict
def llm_answer(query=""):
try:
# Initialize Gemini RAG assistant
model = genai.GenerativeModel(model_name="gemini-2.0-flash-exp")
print("query", query)
response = model.generate_content(query)
print(response.text)
return {"response": response.text, "status": "success"}
except Exception as e:
print(f"Error in Gemini chunking: {e}")
return [
{
"response": "",
"status": "fail",
}
]
@app.post("/get-response")
def get_response(request: QueryRequest):
"""
Endpoint to process a query and get a response from the assistant.
"""
try:
# Initialize AgenticRAG and fetch context
rag = AgenticRAG(query_value=request.query, is_uploaded=request.is_uploaded)
context = rag.query(query_text=request.query, n_results=15)
print("Generate answer form gemini")
# Fetch response from gemini assistant
# response = gemini_rag_assistant.get_response_gemini(
# message=request.query, context_data=context
# )
response = get_crew_response(
query=request.query, context=context, url=request.url
)
print(response)
cleaned_text = "".join(
char for char in response if ord(char) >= 32 or char in "\n\r\t"
)
result = json.loads(cleaned_text)
print(result)
result = {
"response": result["Answer"],
"context": result["context"],
"citations": result["citations"],
}
# print(result)
return result
except ValidationError as e:
raise HTTPException(status_code=422, detail=f"Validation Error: {e}")
except ValueError as e:
raise HTTPException(status_code=400, detail=f"Value Error: {e}")
except Exception as e:
traceback.print_exc() # Log the full traceback
raise HTTPException(status_code=500, detail=f"Internal Server Error: {str(e)}")
@app.post("/llm-response")
def get_response_llm(request: dict):
"""
Endpoint to process a query and get a response from the assistant.
"""
try:
# Initialize AgenticRAG and fetch context
print("Generate answer form gemini")
# Fetch response from gemini assistant
result = llm_answer(query=request["query"])
result = {
"response": result["response"],
}
# print(result)
return result
except ValidationError as e:
raise HTTPException(status_code=422, detail=f"Validation Error: {e}")
except ValueError as e:
raise HTTPException(status_code=400, detail=f"Value Error: {e}")
except Exception as e:
traceback.print_exc() # Log the full traceback
raise HTTPException(status_code=500, detail=f"Internal Server Error: {str(e)}")
@app.get("/health")
def health_check():
"""
Endpoint for health check.
"""
return {"status": "ok"}
@app.post("/delete-file")
async def process_upload_data(request: dict):
"""
Endpoint to retrieve do emedding of new file and store the result in Vector database.
"""
try:
db = VectorStore()
print("deletion started.")
db.delete_documents_by_filename(request["file_path"])
print("deletion end.")
return {"response": 200}
except ValidationError as e:
raise HTTPException(status_code=422, detail=f"Validation Error: {e}")
except ValueError as e:
raise HTTPException(status_code=400, detail=f"Value Error: {e}")
except Exception as e:
traceback.print_exc() # Log the full traceback
raise HTTPException(status_code=500, detail=f"Internal Server Error: {str(e)}")
@app.post("/process-file")
async def process_upload_data(request: dict):
"""
Endpoint to retrieve do emedding of new file and store the result in Vector database.
"""
try:
# Initialize AgenticRAG and fetch context
rag = AgenticRAG(is_uploaded=False)
print("process started.")
rag.process_file(request["file_path"])
print("process end.")
# rag = AgenticRAG(query_value=request.query)
# context = rag.query(query_text=request.query, n_results=10)
# # Fetch response from gemini assistant
# response = await gemini_rag_assistant.get_response(
# message=request.query, context_data=context
# )
# # Ensure response is in correct format
# if not isinstance(response, str):
# raise ValueError("Unexpected response format from gemini_rag_assistant.")
return {"response": 200}
except ValidationError as e:
raise HTTPException(status_code=422, detail=f"Validation Error: {e}")
except ValueError as e:
raise HTTPException(status_code=400, detail=f"Value Error: {e}")
except Exception as e:
traceback.print_exc() # Log the full traceback
raise HTTPException(status_code=500, detail=f"Internal Server Error: {str(e)}")
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=8000)
|