AI BriefingLangChain Blog news
The latest AI and developer news from LangChain Blog, with short summaries.
Visit website →LangChain Integrates Airbyte Sources
LangChain now supports Airbyte sources as document loaders, simplifying data integration.
Xata x LangChain: New Vector Store and Memory Store Integrations
Xata announced integrations with LangChain for vector and memory stores, enhancing data processing capabilities for AI applications.
Wiki Memory: File-Based Memory for AI Agents
LangChain introduced a file-based 'wiki memory' pattern that compresses raw data for AI agents.
Proving the ROI of Agentic AI in Financial Services
This article presents methods for managing the dynamic cost structures of agentic AI in financial services and demonstrating business value.
LangSmith Engine: How to Build Agents That Improve Agents
LangChain has released LangSmith Engine, which analyzes agent traces to identify repetitive errors.
Building Enterprise Due Diligence Agents with Deep Agents
Built an agent combining LangChain Deep Agents and the Parallel API to automate enterprise due diligence workflows.
EU Macroeconomic Analysis with Deep Agents and You.com
Used LangChain's Deep Agents and the You.com API to analyze GDP data for the EU's 27 member states and generate a sourced briefing.
Agent Observability Requires Feedback for Learning
Feedback mechanisms are essential to transform agent observability data into learning resources.
Harmonic Rebuilds Scout with Deep Agents and LangSmith, Achieving 4x Retention
Harmonic rebuilt Scout using Deep Agents and LangSmith, increasing user retention by 4x.
Building a State-Aware Agent Harness with LangSmith
Candidly built an agent harness using LangSmith to track and respond to user states in real time during conversations.
LangSmith LLM Gateway: Runtime Control for Agents
LangSmith LLM Gateway provides runtime control for centrally managing the cost, speed, and data protection of agent model calls.
Building an Auditable VC Research Agent with Perplexity
Built an agent combining the Perplexity Agent API and LangGraph to generate VC investment memo drafts in 90 seconds.
Kay x Cybersyn x LangChain: Processing SEC Disclosure Documents into RAG-Ready Embeddings
Kay and Cybersyn provide a RAG retriever for SEC disclosure data to LangChain, enhancing the efficiency of financial data processing.
Applying OpenAI's RAG Strategy
This article presents concrete implementation methods using LangChain based on OpenAI's RAG experiment results.
Opportunities to Use Auto-Evaluator
LangChain has released 'Auto-Evaluator', an open-source tool for evaluating the performance of LLM question-answering chains.
How to Design Agents for Production Environments
The Rubric Labs team details the technical architecture and logic of deploying the Cal.ai scheduling agent to production using LangChain.
Eden AI x LangChain: LLM, Embeddings, and AI Utilization
Eden AI has integrated with LangChain, enabling easy access to various LLMs and AI tools with a single API key.
Data-Driven Characters
The LangChain team released an open-source repository for generating corpus-based character chatbots.
Qdrant x LangChain: Achieving Final Performance
Integrating Qdrant with LangChain maximizes the performance and resource efficiency of RAG applications.
Connery: Open-Source Plugin Infrastructure for OpenGPTs and LLM Apps
Connery provides open-source plugin infrastructure for integrating third-party services into LLM apps.