Working retrieval with the cli

services/rag/langchain/cli.py

@@ -62,5 +62,56 @@ def enrich(data_dir, collection_name):
         click.echo(f"Error: {str(e)}")
 
 
+@cli.command(
+    name="retrieve",
+    help="Retrieve documents from vector database based on a query",
+)
+@click.argument("query")
+@click.option(
+    "--collection-name",
+    default="documents_langchain",
+    help="Name of the vector store collection",
+)
+@click.option(
+    "--top-k",
+    default=5,
+    help="Number of documents to retrieve",
+)
+def retrieve(query, collection_name, top_k):
+    """Retrieve documents from vector database based on a query"""
+    logger.info(f"Starting retrieval process for query: {query}")
+
+    try:
+        # Import here to avoid circular dependencies
+        from retrieval import search_documents_with_metadata
+
+        # Perform retrieval
+        results = search_documents_with_metadata(
+            query=query,
+            collection_name=collection_name,
+            top_k=top_k
+        )
+
+        if not results:
+            click.echo("No relevant documents found for the query.")
+            return
+
+        click.echo(f"Found {len(results)} relevant documents:\n")
+
+        for i, result in enumerate(results, 1):
+            click.echo(f"{i}. Source: {result['source']}")
+            click.echo(f"   Filename: {result['filename']}")
+            click.echo(f"   Page: {result['page_number']}")
+            click.echo(f"   File Extension: {result['file_extension']}")
+            click.echo(f"   Content Preview: {result['content'][:200]}...")
+            click.echo(f"   Metadata: {result['metadata']}\n")
+
+        logger.info("Retrieval process completed successfully!")
+
+    except Exception as e:
+        logger.error(f"Error during retrieval process: {str(e)}")
+        click.echo(f"Error: {str(e)}")
+
+
 if __name__ == "__main__":
     cli()