Update qdrant_store.py

qdrant_store.py

@@ -1,50 +1,37 @@
-"""Module for interacting with Qdrant vector store using Ollama embeddings.
+"""Wrapper around QdrantVectorStore using Ollama embeddings.
+
+This module is intentionally lightweight and can be imported from any
+context without requiring the caller to set up a package structure.
 """
 
-from typing import List, Dict, Any
+import os
+import sys
+
+# Ensure the current directory is in sys.path so that relative imports work
+sys.path.append(os.path.dirname(__file__))
 
 from langchain_ollama import OllamaEmbeddings
 from langchain_qdrant import QdrantVectorStore
-from qdrant_client import QdrantClient
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from typing import List, Dict
 
 class QdrantStore:
-    """Wrapper around QdrantVectorStore.
+    """Wrapper around QdrantVectorStore using Ollama embeddings."""
 
-    Parameters
-    ----------
-    collection_name: str
-        Name of the Qdrant collection.
-    host: str
-        Qdrant host URL.
-    port: int
-        Qdrant port.
-    """
-
-    def __init__(self, collection_name: str = "rag_collection", host: str = "localhost", port: int = 6333):
-        self.collection_name = collection_name
-        self.client = QdrantClient(host=host, port=port)
+    def __init__(self, host: str = "localhost", port: int = 6333, collection_name: str = "knowledge_base"):
         self.embeddings = OllamaEmbeddings(model="nomic-embed-text")
-        # Create collection if not exists
-        if collection_name not in self.client.get_collections().collections:
-            self.client.recreate_collection(collection_name=collection_name, vectors_config={"size": 512, "distance": "Cosine"})
-        self.store = QdrantVectorStore.from_existing_collection(
+        self.store = QdrantVectorStore(
+            url=f"http://{host}:{port}",
             collection_name=collection_name,
-            embedding=self.embeddings,
-            client=self.client,
+            embeddings=self.embeddings,
         )
 
-    def add_documents(self, documents: List[str], titles: List[str] | None = None, metadatas: List[Dict[str, Any]] | None = None) -> None:
-        """Add documents to the collection.
+    def add_document(self, content: str, title: str) -> None:
+        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+        chunks = splitter.split_text(content)
+        metadatas = [{"title": title, "source": title} for _ in chunks]
+        self.store.add_texts(chunks, metadatas=metadatas)
 
-        Each document is added as a separate vector. If titles or metadatas are provided, they are attached.
-        """
-        if titles is None:
-            titles = [f"doc_{i}" for i in range(len(documents))]
-        if metadatas is None:
-            metadatas = [{} for _ in range(len(documents))]
-        self.store.add_texts(texts=documents, metadatas=metadatas, ids=titles)
-
-    def search(self, query: str, k: int = 5) -> List[Dict[str, Any]]:
-        """Semantic search returning list of dicts with 'content' and 'metadata'."""
-        results = self.store.similarity_search_with_score(query, k=k)
-        return [{"content": r[0].page_content, "metadata": r[0].metadata, "score": r[1]} for r in results]
+    def search(self, query: str, k: int = 5) -> List[Dict]:
+        results = self.store.similarity_search(query, k=k)
+        return [{"content": doc.page_content, "metadata": doc.metadata} for doc in results]