File size: 4,126 Bytes
9514a77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python3
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from typing import List, Optional
import logging
import time
import json
from pathlib import Path

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

STATUS_FILE = Path('/tmp/setup_status.json')
READY_FLAG = Path('/tmp/faiss_ready')

def get_setup_status():
    if not STATUS_FILE.exists():
        return {'status': 'initializing', 'message': 'Setup não iniciado', 'progress': 0}
    try:
        with open(STATUS_FILE) as f:
            return json.load(f)
    except:
        return {'status': 'unknown', 'message': 'Erro ao ler status', 'progress': 0}

def is_ready():
    return READY_FLAG.exists()

query_engine = None

def get_query_engine():
    global query_engine
    if query_engine is None:
        if not is_ready():
            raise HTTPException(status_code=503, detail="RAG em construção. Tente em alguns minutos.")
        logger.info("Carregando QueryEngine...")
        from query_engine import QueryEngine
        query_engine = QueryEngine()
        logger.info("✅ QueryEngine carregado!")
    return query_engine

app = FastAPI(title="Para.AI RAG Cluster (LangChain)", version="1.0.0")

class EmbeddingSearchRequest(BaseModel):
    query: str
    top_k: int = 10
    return_embeddings: bool = False

class KeywordSearchRequest(BaseModel):
    keywords: List[str]
    operator: str = "AND"
    top_k: int = 20

class IDSearchRequest(BaseModel):
    ids: List[str]
    return_embeddings: bool = False

@app.get("/")
async def root():
    setup_status = get_setup_status()
    ready = is_ready()

    response = {"status": "online", "rag_ready": ready, "setup": setup_status, "backend": "LangChain + FAISS (CPU)"}

    if ready and query_engine:
        response["cluster_id"] = query_engine.config.get('cluster_id')
        response["chunk_range"] = [query_engine.config.get('chunk_start'), query_engine.config.get('chunk_end')]

    return response

@app.get("/setup/status")
async def setup_status():
    return get_setup_status()

@app.get("/health")
async def health():
    return {"status": "ok", "timestamp": time.time()}

@app.post("/search/embedding")
async def search_embedding(request: EmbeddingSearchRequest):
    engine = get_query_engine()
    try:
        start = time.time()
        results = engine.search_by_embedding(request.query, request.top_k, request.return_embeddings)
        results['query_time_ms'] = round((time.time() - start) * 1000, 2)
        return results
    except Exception as e:
        logger.error(f"Erro: {e}")
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/search/keywords")
async def search_keywords(request: KeywordSearchRequest):
    engine = get_query_engine()
    try:
        start = time.time()
        results = engine.search_by_keywords(request.keywords, request.operator, request.top_k)
        results['query_time_ms'] = round((time.time() - start) * 1000, 2)
        return results
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/search/by_id")
async def search_by_id(request: IDSearchRequest):
    engine = get_query_engine()
    try:
        start = time.time()
        results = engine.search_by_ids(request.ids, request.return_embeddings)
        results['query_time_ms'] = round((time.time() - start) * 1000, 2)
        return results
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.get("/cluster/info")
async def cluster_info():
    engine = get_query_engine()
    try:
        info = engine.get_cluster_info()
        info['uptime_seconds'] = round(time.time() - app.state.start_time, 2)
        return info
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.on_event("startup")
async def startup_event():
    app.state.start_time = time.time()
    logger.info("="*80)
    logger.info("🚀 Para.AI RAG (LangChain + FAISS) ONLINE")
    logger.info("="*80)

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=7860)