Spaces:
Sleeping
Sleeping
File size: 6,579 Bytes
ba4ad33 | 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 | from fastapi import FastAPI, HTTPException, Request
from fastapi.staticfiles import StaticFiles
from fastapi.concurrency import run_in_threadpool
import os
from .schemas import SearchRequest, SearchResponse, CompoundResult
from .services import (
initialize_engine,
get_search_results,
get_search_results_retrieval_only,
get_system_stats
)
app = FastAPI(
title="Chemical RAG System v2.1",
version="2.1.0",
description="FAISS-IVF Retrieval-Augmented Generation for 1M+ chemical compounds"
)
# Mount static files
if os.path.exists("app/static"):
app.mount("/static", StaticFiles(directory="app/static"), name="static")
@app.on_event("startup")
async def startup_event():
"""Initialize the engine on startup with centralized logic."""
try:
initialize_engine()
print("[SUCCESS] API startup successful (v2.1.0)")
except Exception as e:
import traceback
print(f"[ERROR] Startup failed: {str(e)}")
traceback.print_exc()
@app.get("/")
async def root():
"""Health check endpoint."""
return {
"status": "running",
"service": "Chemical RAG System with FAISS-IVF",
"version": "2.1.0",
"endpoints": {
"/search/retrieval-only": "Fast retrieval using FAISS-IVF (no LLM)",
"/search/full-rag": "Full RAG pipeline with LLM explanation",
"/stats": "System statistics",
"/health": "Health check"
}
}
@app.get("/health")
async def health():
"""Health check with detailed status."""
stats = get_system_stats()
return {
"status": "healthy",
"service": "Chemical RAG System",
"version": "2.1.0",
"system": stats,
"features": [
"FAISS-IVF Indexing (1M+ compound support)",
"Fast retrieval (<100ms)",
"LLM Explanations (Optional)",
"Chemical accuracy preserved"
]
}
@app.post("/search/retrieval-only", response_model=SearchResponse)
async def search_retrieval_only(payload: SearchRequest, http_request: Request):
"""
⚡ FAST RETRIEVAL ENDPOINT (No LLM generation)
Uses FAISS-IVF for ultra-fast chemical similarity search.
Performance:
- 1M compounds: <100ms
- No LLM overhead
- Chemical accuracy maintained
Response includes:
- SMILES and similarity scores
- Compound metadata (name, CID, MW)
- No explanations
"""
# Validate SMILES
if not payload.smiles or len(payload.smiles.strip()) == 0:
raise HTTPException(status_code=400, detail="SMILES string cannot be empty")
if payload.top_k < 1 or payload.top_k > 100:
raise HTTPException(status_code=400, detail="top_k must be between 1 and 100")
try:
# Get base URL from request
base_url = str(http_request.base_url).rstrip('/')
# Run retrieval-only search (no generation)
results, query_smiles = await run_in_threadpool(
get_search_results_retrieval_only,
payload.smiles.strip(),
payload.top_k,
base_url
)
# Convert to response model (empty results is OK - just no matches found)
compound_results = [
CompoundResult(
smiles=r["smiles"],
similarity_score=r["similarity_score"],
image=r.get("image"),
explanation=None, # Retrieval-only mode
cid=r.get("cid"),
name=r.get("name")
)
for r in results
]
return SearchResponse(
results=compound_results,
query_smiles=query_smiles,
total_results=len(compound_results)
)
except HTTPException:
raise
except Exception as e:
# Check if it's a SMILES validation issue
error_msg = str(e).lower()
if "smiles" in error_msg or "invalid" in error_msg:
raise HTTPException(status_code=400, detail=f"Invalid SMILES string: {str(e)}")
raise HTTPException(status_code=500, detail=str(e))
@app.post("/search/full-rag", response_model=SearchResponse)
async def search_full_rag(payload: SearchRequest, http_request: Request):
"""
🤖 FULL RAG ENDPOINT (Retrieval + LLM Explanation)
Combines FAISS-IVF retrieval with Llama-3.1-8B explanations.
Performance:
- 1M compounds: <500ms (FAISS + LLM)
- Full RAG pipeline
- Chemical explanations included
Response includes:
- SMILES and similarity scores
- Compound metadata (name, CID, MW)
- LLM-generated explanations of why compounds are similar
"""
# Validate SMILES
if not payload.smiles or len(payload.smiles.strip()) == 0:
raise HTTPException(status_code=400, detail="SMILES string cannot be empty")
if payload.top_k < 1 or payload.top_k > 100:
raise HTTPException(status_code=400, detail="top_k must be between 1 and 100")
try:
# Get base URL from request
base_url = str(http_request.base_url).rstrip('/')
# Run full RAG search with explanations
results, query_smiles = await run_in_threadpool(
get_search_results,
payload.smiles.strip(),
payload.top_k,
payload.explain, # Use the explain parameter
base_url
)
# Convert to response model (empty results is OK - just no matches found)
compound_results = [
CompoundResult(
smiles=r["smiles"],
similarity_score=r["similarity_score"],
image=r.get("image"),
explanation=r.get("explanation"), # LLM explanation included
cid=r.get("cid"),
name=r.get("name")
)
for r in results
]
return SearchResponse(
results=compound_results,
query_smiles=query_smiles,
total_results=len(compound_results)
)
except HTTPException:
raise
except Exception as e:
# Check if it's a SMILES validation issue
error_msg = str(e).lower()
if "smiles" in error_msg or "invalid" in error_msg:
raise HTTPException(status_code=400, detail=f"Invalid SMILES string: {str(e)}")
raise HTTPException(status_code=500, detail=str(e))
@app.get("/stats")
async def stats():
"""Get system statistics including FAISS-IVF index info."""
system_stats = get_system_stats()
return system_stats
|