Using Advanced Retrievers in LangChain
More Techniques to Improve Retrieval Quality If you’ve ever hit the wall with basic retrievers, it’s time to gear up…
Using Self-Critiquing Chains in LangChain
Enhancing Trustworthiness and Accountability through LangChain's ConstitutionalChain Introduction Building LLM-driven technologies is not just about creating systems that can…
Assessing LLM Output with LangChain’s String Evaluators
An In-depth Look into Evaluating AI Outputs, Custom Criteria, and the Integration of Constitutional Principles Photo by Markus Winkler on Unsplash…
Retrieval Part 2: Text Embeddings
Explore How LangChain’s Semantic Search Allows You To Transform Data Retrieval and Information Discovery In this blog post, I’ll show…
Mastering Document Chains in LangChain
A Deep Dive into LangChain’s Powerful Tools for Text Analysis The ability to efficiently handle and process large volumes of text…
Plan-and-Execute Agents in Langchain
Evolution from Action to Plan-and-Execute Traditional “Action Agents” followed a framework where user input was received, the agent decided on…
Using the ReAct Framework in LangChain
Both ways: Using off-the-shelf agents and LCEL ReAct Framework for Prompting ReAct, which stands for Reasoning + Acting, is a prompting…