Spaces:
Sleeping
Sleeping
File size: 7,617 Bytes
5a21d6e a5aba38 5a21d6e a5aba38 79d4fd5 a5aba38 79d4fd5 a5aba38 5a21d6e a5aba38 79d4fd5 a5aba38 | 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 | from typing import List, Dict, Any, Optional, Set
from langchain_qdrant import QdrantVectorStore
from langchain_core.documents import Document
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams, Filter, FieldCondition, MatchValue
from config import (
QDRANT_PATH,
COLLECTION_NAME,
EMBEDDING_DIMENSION,
USE_MEMORY_MODE
)
from embeddings import get_embedder
from qdrant_client_manager import get_qdrant_client
class VectorStore:
"""Qdrant vector store wrapper."""
def __init__(
self,
path: str = QDRANT_PATH,
collection_name: str = COLLECTION_NAME,
use_memory: bool = USE_MEMORY_MODE,
embedder=None
):
self.collection_name = collection_name
self.use_memory = use_memory
self.path = path
# Use shared Qdrant client to prevent multiple instance conflicts
self._client = get_qdrant_client()
self._ensure_collection_exists()
self._embedder = embedder or get_embedder()
self._vector_store = QdrantVectorStore(
client=self._client,
collection_name=self.collection_name,
embedding=self._embedder
)
def _ensure_collection_exists(self):
"""Create collection if it doesn't exist."""
collections = self._client.get_collections().collections
names = [c.name for c in collections]
if self.collection_name not in names:
self._client.create_collection(
collection_name=self.collection_name,
vectors_config=VectorParams(
size=EMBEDDING_DIMENSION,
distance=Distance.COSINE
)
)
def add_documents(
self,
texts: List[str],
metadatas: Optional[List[Dict[str, Any]]] = None
) -> List[str]:
"""Add documents to the vector store."""
if not texts:
return []
if metadatas is None:
metadatas = [{} for _ in texts]
documents = [
Document(page_content=text, metadata=meta)
for text, meta in zip(texts, metadatas)
]
ids = self._vector_store.add_documents(documents)
return ids
def search(self, query: str, top_k: int = 20) -> List[Dict[str, Any]]:
"""Search for similar documents."""
results = self._vector_store.similarity_search_with_score(
query=query,
k=top_k
)
formatted = []
for doc, score in results:
formatted.append({
"id": doc.metadata.get("_id", ""),
"score": score,
"text": doc.page_content,
"source": doc.metadata.get("source", "Unknown"),
"chunk_index": doc.metadata.get("chunk_index", -1),
"page_number": doc.metadata.get("page_number", -1),
"metadata": doc.metadata
})
return formatted
def get_collection_stats(self) -> Dict[str, Any]:
"""Get collection statistics."""
try:
info = self._client.get_collection(self.collection_name)
count = info.points_count or 0
return {
"name": self.collection_name,
"vectors_count": count,
"points_count": count,
"status": str(info.status)
}
except Exception:
return {
"name": self.collection_name,
"vectors_count": 0,
"points_count": 0,
"status": "error"
}
def clear_collection(self):
"""Delete and recreate the collection."""
self._client.delete_collection(self.collection_name)
self._ensure_collection_exists()
self._vector_store = QdrantVectorStore(
client=self._client,
collection_name=self.collection_name,
embedding=self._embedder
)
def collection_exists(self) -> bool:
"""Check if collection has documents."""
stats = self.get_collection_stats()
return stats["points_count"] > 0
def document_exists(self, source: str) -> bool:
"""
Check if a document with the given source name exists in the collection.
Args:
source: The source filename to check for
Returns:
True if document exists, False otherwise
"""
try:
result = self._client.scroll(
collection_name=self.collection_name,
scroll_filter=Filter(
must=[
FieldCondition(
key="metadata.source",
match=MatchValue(value=source)
)
]
),
limit=1,
with_payload=False,
with_vectors=False
)
points, _ = result
return len(points) > 0
except Exception:
return False
def get_loaded_sources(self) -> Set[str]:
"""
Get set of all unique source names in the collection.
Returns:
Set of source filenames
"""
sources = set()
try:
offset = None
while True:
result = self._client.scroll(
collection_name=self.collection_name,
limit=100,
offset=offset,
with_payload=True,
with_vectors=False
)
points, offset = result
for point in points:
if point.payload:
# Check both possible metadata structures
source = None
if "metadata" in point.payload and isinstance(point.payload["metadata"], dict):
source = point.payload["metadata"].get("source")
if not source:
source = point.payload.get("source")
if source:
sources.add(source)
if offset is None:
break
return sources
except Exception:
return sources
_vector_store_instance = None
def get_vector_store() -> VectorStore:
"""Return singleton vector store instance."""
global _vector_store_instance
if _vector_store_instance is None:
_vector_store_instance = VectorStore()
return _vector_store_instance
def reset_vector_store():
"""Reset singleton for testing."""
global _vector_store_instance
if _vector_store_instance is not None:
try:
_vector_store_instance.clear_collection()
except Exception:
pass
_vector_store_instance = None
if __name__ == "__main__":
store = VectorStore(use_memory=True)
texts = ["Atlas ERP sistemi.", "Finans modülü özellikleri."]
metadatas = [
{"source": "test.pdf", "chunk_index": 0},
{"source": "test.pdf", "chunk_index": 1}
]
store.add_documents(texts, metadatas)
print(f"Stats: {store.get_collection_stats()}")
results = store.search("ERP nedir?", top_k=2)
for r in results:
print(f"Score: {r['score']:.4f} - {r['text'][:50]}")
|