LangFriend: a Journal with Long-Term Memory One of the concepts we are most interested in at LangChain is memory. Whenever we are interested in a concept, we like to build an
Open Source Extraction Service Earlier this month we announced our most recent OSS use-case accelerant: a service for extracting structured data from unstructured sources, such as text and PDF
LangChain Integrates NVIDIA NIM for GPU-optimized LLM Inference in RAG Roughly a year and a half ago, OpenAI launched ChatGPT and the generative AI era really kicked off. Since then we’ve seen rapid growth
Enhancing RAG-based application accuracy by constructing and leveraging knowledge graphs A practical guide to constructing and retrieving information from knowledge graphs in RAG applications with Neo4j and LangChain Editor's Note: the following is
Benchmarking Query Analysis in High Cardinality Situations Several key use cases for LLMs involve returning data in a structured format. Extraction is one such use case - we recently highlighted this with
Iterating Towards LLM Reliability with Evaluation Driven Development Editor's Note: the following is a guest blog post from the Devin Stein, CEO of Dosu. Dosu is an engineering teammate that helps
Use Case Accelerant: Extraction Service Today we’re excited to announce our newest OSS use-case accelerant: an extraction service. LLMs are a powerful tool for extracting structured data from unstructured
JSON agents with Ollama & LangChain Learn to implement an open-source Mixtral agent that interacts with a graph database Neo4j through a semantic layer Editor's note: This post is
Supercharging If-Statements With Prompt Classification Using Ollama and LangChain Editor's Note: Andrew Nguonly has been building one of the more impressive projects we've seen recently - an LLM co-pilot for
Rakuten Group builds with LangChain and LangSmith to deliver premium products for its business clients and employees Rakuten Group is well known for operating one of the largest online shopping malls in Japan. The company has 70+ businesses in fields such as
How Dataherald Makes Natural Language to SQL Easy Editor's Note: we're excited to feature this guest post from the Dataherald team. Text-to-SQL is a HUGE use case, and Dataherald
Plan-and-Execute Agents Plan and execute agents promise faster, cheaper, and more performant task execution over previous agent designs. Learn how to build 3 types of planning agents in LangGraph in this post.