Publish solution for task 6a02e23da6fe2e4ac16acf65: update load_documents.py

load_documents.py

@@ -1,14 +1,13 @@
-"""Utility script to load documents from a directory into the Qdrant vector store.
+# Utility script to load documents from a directory into the Chroma vector store.
-
+#
-The script walks through the specified directory, reads all .txt files, splits them into chunks using
+# The script walks through the specified directory, reads all .txt files, splits them into chunks using
-`RecursiveCharacterTextSplitter`, embeds the chunks with `OllamaEmbeddings`, and stores them in the
+# `RecursiveCharacterTextSplitter`, embeds the chunks with `OllamaEmbeddings`, and stores them in the
-local Qdrant collection via the helper functions defined in :mod:`main`.
+# local Chroma collection via the helper functions defined in :mod:`main`.
-
+#
-Usage:
+# Usage:
-    python load_documents.py /path/to/docs
+#     python load_documents.py /path/to/docs
-
+#
-The script prints the number of documents added.
+# The script prints the number of documents added.
-"""
 
 import os
 import sys
@@ -48,7 +47,9 @@ def load_documents_from_dir(directory: str) -> int:
         title = file_path.stem
         documents = chunk_document(content, title)
         ids = [str(uuid4()) for _ in documents]
-        vector_store.add_documents(documents, ids=ids)
+        embeddings = embedding.embed_documents([doc.page_content for doc in documents])
+        collection = vector_store.get_collection(name="rag_memory")
+        collection.add(ids=ids, documents=[doc.page_content for doc in documents], embeddings=embeddings, metadatas=[doc.metadata for doc in documents])
         total_chunks += len(documents)
     return total_chunks