"Research Assistant": Exploring UXs Besides Chat TLDR: We’re excited to announce a new LangChain template for helping with research, heavily inspired by and in collaboration with the GPT Researcher team.
LangChain Expands Collaboration with Microsoft Today, we’re thrilled to announce a collaboration between LangChain and Microsoft. LangChain helps developers build context-aware reasoning applications and powers some of the
Query Construction Key Links * Text-to-metadata: Updated self-query docs and template * Text-to-SQL+semantic: Cookbook and template There's great interest in seamlessly
Morningstar Intelligence Engine puts personalized investment insights at analysts' fingertips Challenge Financial services is one of the most data-driven industries and financial professionals are always hungry for more data and better tools to drive
Parallel Function Calling for Structured Data Extraction Important Links: * Cookbook for extraction using parallel function calling One of the biggest use cases for language models that we see is in extraction. This
♠️ SPADE: Automatically Digging up Evals based on Prompt Refinements Written by Shreya Shankar (UC Berkeley) in collaboration with Haotian Li (HKUST), Will Fu-Hinthorn (LangChain), Harrison Chase (LangChain), J.D. Zamfirescu-Pereira (UC Berkeley)
Implementing advanced RAG strategies with Neo4j Editor's note: We're excited to share this blogpost as it covers several of the advanced retrieval strategies we introduced in the
Embeddings Drive the Quality of RAG: Voyage AI in Chat LangChain Editor's Note: This post was written by the Voyage AI team. This post demonstrates that the choice of embedding models significantly impacts the
LangChain Templates Today we're excited to announce the release of LangChain Templates. LangChain Templates offers a collection of easily deployable reference architectures that anyone can
Announcing Data Annotation Queues 💡Data Annotation Queues are a new feature in LangSmith, our developer platform aimed at helping bring LLM applications from prototype to production. Sign up for
Query Transformations Naive RAG typically splits documents into chunks, embeds them, and retrieves chunks with high semantic similarity to a user question. But, this present a few
LangChain's First Birthday It’s LangChain’s first birthday! It’s been a really exciting year! We worked with thousands of developers building LLM applications and tooling. We
