Elasticsearch and LangChain collaborate on a new retrieval agent template for LangGraph for agentic apps

What is LangGraph?

About LangGraph’s default Elasticsearch template

Get building

LangChain and Elasticsearch accelerate time to build AI retrieval agents

Explore Elastic's Playground and learn how to use it to experiment with RAG applications using Bedrock Anthropic Models & Elasticsearch.

A/B test LLMs & retrieval with Playground inference via Amazon Bedrock

Using Elastic's Playground

Using retrievers and hybrid search for the best context

Use Playground to ship conversational search—quickly

Build, test, fun with Playground

Elastic's Playground is a low-code interface that enables developers to iterate and build production RAG applications by A/B testing LLMs, tuning prompts, and chunking data.

What is Elastic's Playground?

Elastic Playground: RAG with Bedrock Anthropic & Elasticsearch

Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes

Learn about Elastic's Playground and how to use it to experiment with RAG applications using Elasticsearch.

What is Playground?

A/B test LLMs and choose different inference providers

The best context window with retrievers and hybrid search

Using the Playground

Connect to your LLM

Chat with your data

Indexing a PDF document with BM25 with Python

Chatting with your data with Playground

What happens behind the scenes?

Asking a question

Asking a follow up question

Context

Improving retrieval with Semantic Search and Chunking

Sparse Vector Semantic search with ELSER

Chunking and ingesting the PDF with pyPDF and LangChain

Creating an ELSER inference endpoint

Ingesting into Elasticsearch

Splitting pages into passages and ingesting into Elasticsearch

See it in action on Playground

Hybrid Search made simple

Improve the LLM’s answers

System prompt

Optimizing context

Final Step! Integrate RAG into your application

Conclusion

Build, test, fun with playground

Playground is a low code interface for developers to explore grounding LLMs of their choice with their own private data, in minutes.

Using Elastic's Playground to experiment with RAG applications

Playground: Experiment with RAG applications with Elasticsearch in minutes

Learn about Retrieval Augmented Generation (RAG) and how it can help improve the quality of an LLM's generated responses by providing relevant source knowledge as context.

Challenges with Generative AI

Lack of domain knowledge

Frozen parametric knowledge

Hallucinations

Expensive to train

How does RAG help solve this problem?

How does RAG work?

RAG pipeline flow

Retrieval of source knowledge

Advantages of RAG

Grounded in source knowledge

Citing sources in responses

RAG in action

Build a context

Prompt template

Question

Challenges with RAG

Precise dense vectors

Large context

A RAG pipeline typically has the following main components: 1) Data: A collection of data (e.g documents, webpages) that contain relevant information to answer questions. 2) Retrieval: A retrieval strategy that can retrieve relevant source knowledge from the data. 3) Generation: With the relevant source knowledge, generate a response with the help of an LLM.

How does Retrieval Augmented Generation (RAG) work?

Retrieval Augmented Generation: Refine LLM Responses with RAG

Retrieval Augmented Generation (RAG)

Author

Joe McElroy

Articles

LangChain and Elasticsearch accelerate time to build AI retrieval agents

Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes

Playground: Experiment with RAG applications with Elasticsearch in minutes

Retrieval Augmented Generation (RAG)