Create embed.py

embed.py

@@ -0,0 +1,32 @@
+import uuid
+from langchain_community.vectorstores import Qdrant
+from qdrant_client import  models
+from utils import setup_qdrant_client,setup_openai_embeddings
+
+
+def embed_documents_into_qdrant(documents, api_key, qdrant_url, qdrant_api_key, collection_name="Lex-v1"):
+    """Embed documents into Qdrant."""
+    embeddings_model = setup_openai_embeddings(api_key)
+    client = setup_qdrant_client(qdrant_url, qdrant_api_key)
+    qdrant = Qdrant(client=client, collection_name=collection_name, embeddings=embeddings_model)
+    try:
+        qdrant.add_documents(documents)
+    except Exception as e:
+        print("Failed to embed documents:", e)
+
+def embed_documents_with_unique_collection(documents, api_key, qdrant_url, qdrant_api_key, collection_name=None):
+    """Embed documents into a unique Qdrant collection."""
+    if not collection_name:
+        collection_name = f"session-{uuid.uuid4()}"
+        client = setup_qdrant_client(qdrant_url, qdrant_api_key)
+        client.create_collection(
+            collection_name=collection_name,
+            vectors_config=models.VectorParams(size=1536, distance=models.Distance.COSINE)
+        )
+    embeddings_model = setup_openai_embeddings(api_key)
+    qdrant = Qdrant(client=client, collection_name=collection_name, embeddings=embeddings_model)
+    try:
+        qdrant.add_documents(documents)
+    except Exception as e:
+        print("Failed to embed documents:", e)
+    return collection_name