Spaces:
Running
Running
File size: 10,876 Bytes
1d10b0a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
"""FastAPI backend service for RAG application."""
from fastapi import FastAPI, HTTPException, BackgroundTasks
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel, Field
from typing import List, Optional, Dict
import uvicorn
from datetime import datetime
import os
from config import settings
from dataset_loader import RAGBenchLoader
from vector_store import ChromaDBManager
from llm_client import GroqLLMClient, RAGPipeline
from trace_evaluator import TRACEEvaluator
# Initialize FastAPI app
app = FastAPI(
title="RAG Capstone API",
description="API for RAG system with TRACE evaluation",
version="1.0.0"
)
# Add CORS middleware
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Global state
rag_pipeline: Optional[RAGPipeline] = None
vector_store: Optional[ChromaDBManager] = None
current_collection: Optional[str] = None
# Request/Response models
class DatasetLoadRequest(BaseModel):
"""Request model for loading dataset."""
dataset_name: str = Field(..., description="Name of the dataset")
num_samples: int = Field(50, description="Number of samples to load")
chunking_strategy: str = Field("hybrid", description="Chunking strategy")
chunk_size: int = Field(512, description="Size of chunks")
overlap: int = Field(50, description="Overlap between chunks")
embedding_model: str = Field(..., description="Embedding model name")
llm_model: str = Field("llama-3.1-8b-instant", description="LLM model name")
groq_api_key: str = Field(..., description="Groq API key")
class QueryRequest(BaseModel):
"""Request model for querying."""
query: str = Field(..., description="User query")
n_results: int = Field(5, description="Number of documents to retrieve")
max_tokens: int = Field(1024, description="Maximum tokens to generate")
temperature: float = Field(0.7, description="Sampling temperature")
class QueryResponse(BaseModel):
"""Response model for query."""
query: str
response: str
retrieved_documents: List[Dict]
timestamp: str
class EvaluationRequest(BaseModel):
"""Request model for evaluation."""
num_samples: int = Field(10, description="Number of test samples")
class CollectionInfo(BaseModel):
"""Collection information model."""
name: str
count: int
metadata: Dict
# API endpoints
@app.get("/")
async def root():
"""Root endpoint."""
return {
"message": "RAG Capstone API",
"version": "1.0.0",
"docs": "/docs"
}
@app.get("/health")
async def health_check():
"""Health check endpoint."""
return {
"status": "healthy",
"timestamp": datetime.now().isoformat()
}
@app.get("/datasets")
async def list_datasets():
"""List available datasets."""
return {
"datasets": settings.ragbench_datasets
}
@app.get("/models/embedding")
async def list_embedding_models():
"""List available embedding models."""
return {
"embedding_models": settings.embedding_models
}
@app.get("/models/llm")
async def list_llm_models():
"""List available LLM models."""
return {
"llm_models": settings.llm_models
}
@app.get("/chunking-strategies")
async def list_chunking_strategies():
"""List available chunking strategies."""
return {
"chunking_strategies": settings.chunking_strategies
}
@app.get("/collections")
async def list_collections():
"""List all vector store collections."""
global vector_store
if not vector_store:
vector_store = ChromaDBManager(settings.chroma_persist_directory)
collections = vector_store.list_collections()
return {
"collections": collections,
"count": len(collections)
}
@app.get("/collections/{collection_name}")
async def get_collection_info(collection_name: str):
"""Get information about a specific collection."""
global vector_store
if not vector_store:
vector_store = ChromaDBManager(settings.chroma_persist_directory)
try:
stats = vector_store.get_collection_stats(collection_name)
return stats
except Exception as e:
raise HTTPException(status_code=404, detail=f"Collection not found: {str(e)}")
@app.post("/load-dataset")
async def load_dataset(request: DatasetLoadRequest, background_tasks: BackgroundTasks):
"""Load dataset and create vector collection."""
global rag_pipeline, vector_store, current_collection
try:
# Initialize dataset loader
loader = RAGBenchLoader()
# Load dataset
dataset = loader.load_dataset(
request.dataset_name,
split="train",
max_samples=request.num_samples
)
if not dataset:
raise HTTPException(status_code=400, detail="Failed to load dataset")
# Initialize vector store
vector_store = ChromaDBManager(settings.chroma_persist_directory)
# Create collection name
collection_name = f"{request.dataset_name}_{request.chunking_strategy}_{request.embedding_model.split('/')[-1]}"
collection_name = collection_name.replace("-", "_").replace(".", "_")
# Load data into collection
vector_store.load_dataset_into_collection(
collection_name=collection_name,
embedding_model_name=request.embedding_model,
chunking_strategy=request.chunking_strategy,
dataset_data=dataset,
chunk_size=request.chunk_size,
overlap=request.overlap
)
# Initialize LLM client
llm_client = GroqLLMClient(
api_key=request.groq_api_key,
model_name=request.llm_model,
max_rpm=settings.groq_rpm_limit,
rate_limit_delay=settings.rate_limit_delay
)
# Create RAG pipeline
rag_pipeline = RAGPipeline(llm_client, vector_store)
current_collection = collection_name
return {
"status": "success",
"collection_name": collection_name,
"num_documents": len(dataset),
"message": f"Collection '{collection_name}' created successfully"
}
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error loading dataset: {str(e)}")
@app.post("/query", response_model=QueryResponse)
async def query_rag(request: QueryRequest):
"""Query the RAG system."""
global rag_pipeline
if not rag_pipeline:
raise HTTPException(
status_code=400,
detail="RAG pipeline not initialized. Load a dataset first."
)
try:
result = rag_pipeline.query(
query=request.query,
n_results=request.n_results,
max_tokens=request.max_tokens,
temperature=request.temperature
)
result["timestamp"] = datetime.now().isoformat()
return result
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error processing query: {str(e)}")
@app.get("/chat-history")
async def get_chat_history():
"""Get chat history."""
global rag_pipeline
if not rag_pipeline:
raise HTTPException(
status_code=400,
detail="RAG pipeline not initialized. Load a dataset first."
)
return {
"history": rag_pipeline.get_chat_history()
}
@app.delete("/chat-history")
async def clear_chat_history():
"""Clear chat history."""
global rag_pipeline
if not rag_pipeline:
raise HTTPException(
status_code=400,
detail="RAG pipeline not initialized. Load a dataset first."
)
rag_pipeline.clear_history()
return {
"status": "success",
"message": "Chat history cleared"
}
@app.post("/evaluate")
async def run_evaluation(request: EvaluationRequest):
"""Run TRACE evaluation."""
global rag_pipeline, current_collection
if not rag_pipeline:
raise HTTPException(
status_code=400,
detail="RAG pipeline not initialized. Load a dataset first."
)
try:
# Get dataset name from collection metadata
collection_metadata = vector_store.current_collection.metadata
dataset_name = current_collection.split("_")[0] if current_collection else "hotpotqa"
# Get test data
loader = RAGBenchLoader()
test_data = loader.get_test_data(dataset_name, request.num_samples)
# Prepare test cases
test_cases = []
for sample in test_data:
result = rag_pipeline.query(sample["question"], n_results=5)
test_cases.append({
"query": sample["question"],
"response": result["response"],
"retrieved_documents": [doc["document"] for doc in result["retrieved_documents"]],
"ground_truth": sample.get("answer", "")
})
# Run evaluation
evaluator = TRACEEvaluator()
results = evaluator.evaluate_batch(test_cases)
return {
"status": "success",
"results": results
}
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error during evaluation: {str(e)}")
@app.delete("/collections/{collection_name}")
async def delete_collection(collection_name: str):
"""Delete a collection."""
global vector_store
if not vector_store:
vector_store = ChromaDBManager(settings.chroma_persist_directory)
try:
vector_store.delete_collection(collection_name)
return {
"status": "success",
"message": f"Collection '{collection_name}' deleted"
}
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error deleting collection: {str(e)}")
@app.get("/current-collection")
async def get_current_collection():
"""Get current collection information."""
global current_collection, vector_store
if not current_collection:
return {
"collection": None,
"message": "No collection loaded"
}
try:
stats = vector_store.get_collection_stats(current_collection)
return {
"collection": current_collection,
"stats": stats
}
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error getting collection info: {str(e)}")
if __name__ == "__main__":
uvicorn.run(
"api:app",
host="0.0.0.0",
port=8000,
reload=True
)
|