Spaces:
Sleeping
Sleeping
File size: 8,550 Bytes
73fd1fc aa63765 73fd1fc c16e1c9 73fd1fc c16e1c9 aa63765 73fd1fc aa63765 73fd1fc aa63765 c16e1c9 aa63765 c16e1c9 aa63765 c16e1c9 aa63765 c16e1c9 aa63765 73fd1fc aa63765 73fd1fc aa63765 345b8ff e44e5dd 345b8ff |
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 |
from fastapi import APIRouter, Header, HTTPException, UploadFile, File, Form
from pydantic import BaseModel
from typing import Optional, Dict, Any
from api.mcp_clients.rag_client import RAGClient
from api.services.document_ingestion import (
prepare_ingestion_payload,
process_ingestion,
detect_source_type,
normalize_text,
extract_text_from_file_bytes
)
router = APIRouter()
rag_client = RAGClient()
class IngestRequest(BaseModel):
"""Legacy simple ingestion request"""
content: str
class DocumentIngestRequest(BaseModel):
"""Enhanced ingestion request matching the system prompt specification"""
action: str = "ingest_document"
tenant_id: Optional[str] = None # Can come from header
source_type: Optional[str] = None # pdf | docx | txt | url | raw_text | markdown
content: str
metadata: Optional[Dict[str, Any]] = None
class SearchRequest(BaseModel):
query: str
@router.post("/search")
async def rag_search(
req: SearchRequest,
x_tenant_id: str = Header(None)
):
"""
Search tenant knowledge base using the RAG MCP server.
"""
if not x_tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
results = await rag_client.search(req.query, x_tenant_id)
return {
"tenant_id": x_tenant_id,
"query": req.query,
"results": results
}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/ingest")
async def rag_ingest(
req: IngestRequest,
x_tenant_id: str = Header(None)
):
"""
Legacy ingestion endpoint - simple content ingestion.
Ingest content into tenant knowledge base using the RAG MCP server.
"""
if not x_tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
result = await rag_client.ingest(req.content, x_tenant_id)
return {
"tenant_id": x_tenant_id,
"status": "ok",
**result
}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/ingest-document")
async def rag_ingest_document(
req: DocumentIngestRequest,
x_tenant_id: Optional[str] = Header(None)
):
"""
Enhanced document ingestion endpoint matching the system prompt specification.
Supports:
- PDF, DOCX, TXT, Markdown files
- URLs (fetches content automatically)
- Raw text
- Metadata (filename, url, doc_id)
Expected payload:
{
"action": "ingest_document",
"tenant_id": "...",
"source_type": "pdf | docx | txt | url | raw_text",
"content": "...",
"metadata": {
"filename": "...",
"url": "...",
"doc_id": "..."
}
}
"""
# Use tenant_id from header if not in body (for backward compatibility)
tenant_id = req.tenant_id or x_tenant_id
if not tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
# Prepare ingestion payload (async for URL fetching)
payload = await prepare_ingestion_payload(
tenant_id=tenant_id,
content=req.content,
source_type=req.source_type,
filename=req.metadata.get("filename") if req.metadata else None,
url=req.metadata.get("url") if req.metadata else None,
doc_id=req.metadata.get("doc_id") if req.metadata else None,
metadata=req.metadata
)
# Process ingestion
result = await process_ingestion(payload, rag_client)
return {
"status": "ok",
"message": f"Document ingested successfully. {result.get('chunks_stored', 0)} chunk(s) stored.",
**result
}
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.post("/ingest-file")
async def rag_ingest_file(
file: UploadFile = File(...),
x_tenant_id: Optional[str] = Header(None),
tenant_id: Optional[str] = Form(None)
):
"""
File upload endpoint for binary files (PDF, DOCX, TXT, MD).
Extracts text server-side and ingests into knowledge base.
Usage:
POST /rag/ingest-file
Headers:
x-tenant-id: <tenant_id>
Form Data:
file: <binary file>
tenant_id: <optional, can use header instead>
"""
# Use tenant_id from form or header
tenant_id_value = tenant_id or x_tenant_id
if not tenant_id_value:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
# Read file bytes
file_bytes = await file.read()
if not file_bytes:
raise HTTPException(status_code=400, detail="File is empty")
# Extract text from binary file
try:
extracted_text = extract_text_from_file_bytes(file_bytes, file.filename or "unknown")
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
if not extracted_text or not extracted_text.strip():
raise HTTPException(status_code=400, detail="No text could be extracted from file")
# Prepare ingestion payload
payload = await prepare_ingestion_payload(
tenant_id=tenant_id_value,
content=extracted_text,
source_type=None, # Auto-detect from filename
filename=file.filename,
url=None,
doc_id=None,
metadata=None
)
# Process ingestion
result = await process_ingestion(payload, rag_client)
return {
"status": "ok",
"message": f"File '{file.filename}' ingested successfully. {result.get('chunks_stored', 0)} chunk(s) stored.",
**result
}
except HTTPException:
raise
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/list")
async def rag_list(
limit: int = 1000,
offset: int = 0,
x_tenant_id: str = Header(None)
):
"""
List all documents in tenant knowledge base.
"""
if not x_tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
result = await rag_client.list_documents(x_tenant_id, limit=limit, offset=offset)
return result
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.delete("/delete/{document_id}")
async def rag_delete(
document_id: int,
x_tenant_id: str = Header(None)
):
"""
Delete a specific document by ID from tenant knowledge base.
"""
if not x_tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
result = await rag_client.delete_document(x_tenant_id, document_id)
if "error" in result:
# Check if it's a connection error (500) or not found (404)
error_msg = result["error"]
if "Cannot connect" in error_msg:
raise HTTPException(status_code=503, detail=error_msg)
elif "not found" in error_msg.lower() or "access denied" in error_msg.lower():
raise HTTPException(status_code=404, detail=error_msg)
else:
raise HTTPException(status_code=500, detail=error_msg)
return result
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.delete("/delete-all")
async def rag_delete_all(
x_tenant_id: str = Header(None)
):
"""
Delete all documents for a tenant.
"""
if not x_tenant_id:
raise HTTPException(status_code=400, detail="Missing tenant ID")
try:
result = await rag_client.delete_all_documents(x_tenant_id)
if "error" in result:
error_msg = result["error"]
# Check if it's a connection error (503) or other error
if "Cannot connect" in error_msg:
raise HTTPException(status_code=503, detail=error_msg)
else:
raise HTTPException(status_code=500, detail=error_msg)
return result
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=500, detail=str(e)) |