Never miss a release that matters
AI-powered summaries of every GitHub release.
AI Summaries
Changelogs condensed into clear, actionable insights.
Always Free
Track up to 5 packages at no cost, forever.
Weekly Digest
A curated summary of every release, delivered weekly.
TL;DR
Langflow is more secure with numerous fixes addressing potential vulnerabilities related to code execution, file access, and data exposure, improving overall platform stability.
Fixes Worth Knowing
- Security was significantly improved by blocking public builds of code execution agents and restricting access to logs and sensitive environment variables.
- FAISS (vector database) persistence is now isolated per user, preventing data mixing.
- The platform now validates file paths, preventing potential traversal issues.
- Telemetry is disabled by default.
TL;DR
Langflow now supports running models locally within the assistant (local-model support), expanding options for model deployment and use.
New
- Local Model Support: The Langflow Assistant can now utilize models running locally on your machine.
- IBM WatsonX Integration: IBM WatsonX models are now selectable and runnable within the Langflow Assistant.
Fixes Worth Knowing
- Fixed issues with displaying private flow streams publicly.
- Resolved problems with connecting to SQL databases within the SQL Database component.
- Improved handling of tool calling with agents and IBM models.
- Fixed a bug that caused LangChain chain markers to leak to standard output.
- Addressed a security vulnerability in URL components related to SSRF (Server-Side Request Forgery - a web security exploit).
Before You Upgrade
If you are using URL components, review your flows to ensure they are not vulnerable to SSRF attacks.
TL;DR
Langflow now supports OpenAI’s Assistants API (AI-powered virtual assistants), enabling more complex conversational flows.
Fixes Worth Knowing
- Resolved an issue where the application would crash when attempting to load a flow with missing components.
- Fixed a bug preventing users from deleting flows containing nodes with no connections.
- Corrected a problem with incorrect display of component descriptions in the sidebar.
TL;DR
Langflow now correctly integrates with Pinecone (vector database), resolving previous issues with its implementation.
Fixes Worth Knowing
Pinecone integration is now functional, allowing users to reliably connect and utilize Pinecone for storing and retrieving vector embeddings.
TL;DR
Langflow now correctly integrates with Anthropic LLMs (large language models), resolving a previous issue.
Fixes Worth Knowing
Anthropic LLM integration is now functional, allowing users to utilize this model within Langflow.