Create vector_store.py

vector_store.py

@@ -0,0 +1,39 @@
+# src/core/vector_store.py
+class FAISSVectorStore:
+    def __init__(self, embedding_dim: int = 384):  # GTE-small dimension
+        self.index = faiss.IndexFlatIP(embedding_dim)  # Inner product for cosine similarity
+        self.documents = []
+        self.metadatas = []
+
+    def add_documents(self, chunks: List[str], embeddings: List[List[float]], metadatas: List[Dict]):
+        if not self.index.is_trained:
+            self.index = faiss.IndexIDMap(self.index)
+        
+        self.documents.extend(chunks)
+        self.metadatas.extend(metadatas)
+        
+        # Add embeddings to FAISS index
+        self.index.add(np.array(embeddings))
+
+    def similarity_search(self, query: str, embedder: DocumentEmbedder, k: int = 5) -> List[Dict]:
+        # Embed query
+        query_embedding = embedder.embedding_model.embed_query(query)
+        
+        # Search in FAISS
+        distances, indices = self.index.search(
+            np.array([query_embedding]), k
+        )
+        
+        # Return results with metadata
+        results = []
+        for i, idx in enumerate(indices[0]):
+            if idx == -1:  # FAISS returns -1 for not found
+                continue
+            
+            results.append({
+                "content": self.documents[idx],
+                "metadata": self.metadatas[idx],
+                "score": float(distances[0][i])
+            })
+        
+        return results