3 commits

Author	SHA1	Message	Date
Varsha	e3928e6a29	feat: Implement hybrid search in Milvus (#2644) ... # What does this PR do? This PR implements hybrid search for Milvus DB based on the inbuilt milvus support. To test: ``` pytest tests/unit/providers/vector_io/remote/test_milvus.py -v -s --tb=long --disable-warnings --asyncio-mode=auto ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>	2025-08-07 09:42:03 +02:00
Charlie Doern	d7cc38e934	fix: remove async test markers (fix pre-commit) (#2808) ... # What does this PR do? some async test markers are in the codebase causing pre-commit to fail due to #2744 remove these pytest fixtures ## Test Plan pre-commit passes Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-07-17 21:35:28 -07:00
Varsha	4ae5656c2f	feat: Implement keyword search in milvus (#2231) ... # What does this PR do? This PR adds the keyword search implementation for Milvus. Along with the implementation for remote Milvus, the tests require us to start a Milvus containers locally. In order to verify the implementation, run: ``` pytest tests/unit/providers/vector_io/remote/test_milvus.py -v -s --tb=short --disable-warnings --asyncio-mode=auto ``` You can also test the changes using the below script: ``` #!/usr/bin/env python3 import asyncio import os import uuid from typing import List from llama_stack_client import ( Agent, AgentEventLogger, LlamaStackClient, RAGDocument ) class MilvusRAGDemo: def __init__(self, base_url: str = "http://localhost:8321/"): self.client = LlamaStackClient(base_url=base_url) self.vector_db_id = f"milvus_rag_demo_{uuid.uuid4().hex[:8]}" self.model_id = None self.embedding_model_id = None self.embedding_dimension = None def setup_models(self): """Get available models and select appropriate ones for LLM and embeddings.""" models = self.client.models.list() # Select embedding model embedding_models = [m for m in models if m.model_type == "embedding"] if not embedding_models: raise ValueError("No embedding models found") self.embedding_model_id = embedding_models[0].identifier self.embedding_dimension = embedding_models[0].metadata["embedding_dimension"] def register_vector_db(self): print(f"Registering Milvus vector database: {self.vector_db_id}") response = self.client.vector_dbs.register( vector_db_id=self.vector_db_id, embedding_model=self.embedding_model_id, embedding_dimension=self.embedding_dimension, provider_id="milvus-remote", # Use remote Milvus ) print(f"Vector database registered successfully") return response def insert_documents(self): """Insert sample documents into the vector database.""" print("\nInserting sample documents...") # Sample documents about different topics documents = [ RAGDocument( document_id="ai_ml_basics", content=""" Artificial Intelligence (AI) and Machine Learning (ML) are transforming the world. AI refers to the simulation of human intelligence in machines, while ML is a subset of AI that enables computers to learn and improve from experience without being explicitly programmed. Deep learning, a subset of ML, uses neural networks with multiple layers to process complex patterns in data. Key concepts in AI/ML include: - Supervised Learning: Training with labeled data - Unsupervised Learning: Finding patterns in unlabeled data - Reinforcement Learning: Learning through trial and error - Neural Networks: Computing systems inspired by biological brains """, mime_type="text/plain", metadata={"topic": "technology", "category": "ai_ml"}, ), ] # Insert documents with chunking self.client.tool_runtime.rag_tool.insert( documents=documents, vector_db_id=self.vector_db_id, chunk_size_in_tokens=200, # Smaller chunks for better granularity ) print(f"Inserted {len(documents)} documents with chunking") def test_keyword_search(self): """Test keyword-based search using BM25.""" queries = [ "neural networks", "Python frameworks", "data cleaning", ] for query in queries: response = self.client.vector_io.query( vector_db_id=self.vector_db_id, query=query, params={ "mode": "keyword", # Keyword search "max_chunks": 3, "score_threshold": 0.0, } ) for i, (chunk, score) in enumerate(zip(response.chunks, response.scores)): print(f" {i+1}. Score: {score:.4f}") print(f" Content: {chunk.content[:100]}...") print(f" Metadata: {chunk.metadata}") def run_demo(self): try: self.setup_models() self.register_vector_db() self.insert_documents() self.test_keyword_search() except Exception as e: print(f"Error during demo: {e}") raise def main(): """Main function to run the demo.""" # Check if Llama Stack server is running demo = MilvusRAGDemo() try: demo.run_demo() except Exception as e: print(f"Demo failed: {e}") if __name__ == "__main__": main() ``` [//]: # (## Documentation) --------- Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>	2025-07-14 19:39:55 -04:00