Download as PDF, PPTX
Uploaded byZilliz
Using LLM Agents with Llama 3, LangGraph and Milvus
The document discusses a webinar presentation by Stephen Batifol on using LLM agents with Llama 3, Langgraph, and Milvus, an open-source vector database for generative AI projects. It highlights the ease of setup and integration with popular AI tools, allowing efficient deployment and usage of machine learning applications. The document also covers the Retrieval Augmented Generation (RAG) process and the technical architecture of Milvus for enhancing LLM performance.
More Related Content
Similar to Using LLM Agents with Llama 3, LangGraph and Milvus
Using LLM Agents with Llama 3, LangGraph and Milvus
- 1. Stephen Batifol |Zilliz Zilliz Webinar, July 11 Using LLM Agents with Llama 3, LangGraph and Milvus
- 2. Stephen Batifol Developer Advocate,Zilliz/ Milvus stephen.batifol@zilliz.com linkedin.com/in/stephen-batifol/ @stephenbtl Speaker
- 3. 27K+ GitHub Stars 25M+ Downloads 250+ Contributors 2,600 + Forks Milvus is anopen-source vector database for GenAI projects. pip install on your laptop, plug into popular AI dev tools, and push to production with a single line of code. Easy Setup Pip-install to start coding in a notebook within seconds. Reusable Code Write once, and deploy with one line of code into the production environment Integration Plug into OpenAI, Langchain, LlmaIndex, and many more Feature-rich Dense & sparse embeddings, filtering, reranking and beyond
- 4. Seamless integration withall popular AI toolkits
- 5. | © Copyright8/16/23 Zilliz 5 RAG (Retrieval Augmented Generation)
- 6. Basic Idea Use RAGto force the LLM to work with your data by injecting it via a vector database like Milvus
- 7.
- 8.
- 9. 9 | ©Copyright 8/16/23 Zilliz 9 | © Copyright 8/16/23 Zilliz 01 Tech Stack
- 10. ● Framework forbuilding LLM Applications ● Focus on retrieving data and integrating with LLMs ● Integrations with most AI popular tools 🦜🔗 LangChain
- 11. 🦜🕸 LangGraph byLangChain ● Build Stateful apps with LLMs and Multi-Agents workflow ● Cycles and Branching ● Human-in-the-Loop ● Persistence
- 12. Ollama ● Run LLMsanywhere ● Run Embedding Models
- 14. 14 | ©Copyright 8/16/23 Zilliz 14 | © Copyright 8/16/23 Zilliz 02 Agentic RAG
- 15. Agentic RAG ✅ Multi-turn ✅Query / task planning layer ✅ Tool interface for external environment ✅ Reflection ✅ Memory for personalization
- 16. ● Routing: AdaptiveRAG ○ Route Questions to different retrieval approaches ● Fallback: Corrective RAG ○ Fallback to web search if docs are not relevant to query ● Self-Correction: Self-RAG ○ Try to fix answers with hallucinations or don’t address question General Ideas
- 17. 17 | ©Copyright 8/16/23 Zilliz 17 | © Copyright 8/16/23 Zilliz 03 RAG in action with Milvus Lite
- 18.
- 19. Meta Storage Root QueryData Index Coordinator Service Proxy Proxy etcd Log Broker SDK Load Balancer DDL/DCL DML NOTIFICATION CONTROL SIGNAL Object Storage Minio / S3 / AzureBlob Log Snapshot Delta File Index File Worker Node QUERY DATA DATA Message Storage VECTOR DATABASE Access Layer Query Node Data Node Index Node Milvus Architecture