Langflow

🚀 Langflow Desktop 1.12 is now available Langflow 1.12 brings OpenTelemetry support for better visibility into service health and flow execution, along with a lighter, more modular installation through Langflow Extensions. This release includes: - OpenTelemetry support for traces, metrics, and logs through OTLP Support for OpenTelemetry-compatible backends, including New Relic and Instana - Langflow Extensions update with a smaller default installation and opt-in provider bundles If you are already using Langflow Desktop, upgrade in the application to version 1.12. To install Langflow Desktop for the first time, and to learn more about the new 1.12 features, visit: https://lnkd.in/dDM243VY

Langflow Extensions - Langflow 1.12 A lighter, more modular way to install and extend Langflow. As Langflow grows, so does the number of providers, tools, vector stores, and integrations available to builders. But not every deployment needs every integration installed by default. With the launch of Langflow 1.12, Langflow completes the transition to Extension bundles. Provider integrations are now packaged as installable extensions, making the default Langflow installation smaller while allowing teams to add extra providers only when their flows need them. The default install now includes a curated provider set. Additional bundles can be installed separately for specialized workflows, integrations, and deployment needs. This gives teams more control over what is included in their Langflow environment, helping reduce unnecessary dependencies while keeping the platform flexible. Saved flows continue to open normally, with existing component class names remaining compatible. If a flow requires a provider that is not installed, teams can install the corresponding bundle and continue working without changing the flow structure. Langflow Extensions also create a clearer path for developers to package, validate, and distribute their own components as extensions. Why it matters: - Keeps the default installation lighter - Makes dependency management cleaner - Lets teams install only the providers they need - Supports custom and community-built extensions - Helps Langflow scale as more integrations are added - Makes Langflow easier to maintain across different environments 👉 Explore Langflow Extensions in Langflow 1.12: https://lnkd.in/dSxTf_T8

OpenTelemetry support - Langflow 1.12 Observe Langflow like a production service. Langflow 1.12 adds OpenTelemetry support to help teams monitor service health, investigate latency and errors, and understand how flows execute in production. With standard OTLP, Langflow can emit traces, metrics, and logs to OpenTelemetry-compatible backends, including New Relic and Instana. This is application observability for Langflow itself, not prompt-level LLM tracing. Prompts, completions, tool arguments, and flow payloads are withheld from the default telemetry path. Watch the video and explore OpenTelemetry support in Langflow 1.12: https://lnkd.in/dSxTf_T8

We are taking 25 developers into early access for the next version of Langflow. Building an AI agent is the easy part now. Getting permission to run it inside a real organisation is not. Access control, credential handling, deployment, and knowing what your agents actually did are the things that decide whether an agent ever leaves the prototype stage. That is what we are building, and we want 25 people building it with us. Langflow Champions get pre release builds, a private channel with the maintainers, monthly office hours with the core team, and genuine influence over what ships. Find a bug and we fix it. Tell us a feature is wrong and we change it. Apply Now: https://lnkd.in/d4X5jT6i

🚀 Langflow 1.12 is live Langflow 1.12 introduces OpenTelemetry support, giving teams better visibility into Langflow service health and flow execution as deployments grow in scale and complexity. This release adds support for emitting traces, metrics, and logs through OTLP, making it easier to connect Langflow to OpenTelemetry-compatible observability backends such as New Relic and Instana. What’s new in this release: 🔹 OpenTelemetry support Langflow can now emit telemetry signals that help teams understand how the service is running in production environments. With OpenTelemetry support, teams can monitor Langflow using the observability tools they already rely on, without being locked into a single vendor-specific backend. Langflow can export traces, metrics, and logs through standard OpenTelemetry environment variables. Example: OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 OTEL_SERVICE_NAME=langflow This gives deployment teams a clearer way to observe service health, monitor latency and errors, investigate slow requests, and connect logs with execution traces in production environments. Why it matters: - Makes Langflow easier to monitor in production - Connects Langflow to existing observability stacks - Supports traces, metrics, and logs through standard OTLP - Helps teams operate Langflow more confidently at scale - Improves visibility as workflows and deployments become more complex Also in 1.12: 🔹 Langflow Extensions update Langflow 1.12 completes the transition to Extension bundles, making the default installation lighter and more modular. A curated set of providers is included by default, while additional providers can be installed separately when your flows need them. Saved flows continue to open normally, and existing component class names remain compatible. Before upgrading, review the release notes for packaging and installation changes in this release. 👉 Explore more about Langflow 1.12: https://lnkd.in/dSxTf_T8

When one vector is not enough for RAG Single-vector retrieval works well for many workflows. But when documents get longer, denser, or visually complex, compressing everything into one embedding can lose important context. A long technical report, a PDF full of tables, a slide deck, or a scanned document often contains meaning across tokens, layout, charts, and visual structure. That is where multi-vector retrieval changes the game. In our latest blog, we break down how Langflow 1.11 introduces first-class multi-vector retrieval with the new lfx-nextplaid extension bundle. With NextPlaid, Langflow flows can now use ColBERT-style late interaction and ColPali-style visual document retrieval without custom glue code. What this enables: - Token-level retrieval instead of relying on a single pooled document vector - Better search quality for long and information-dense documents - Visual retrieval for PDFs, tables, charts, slide decks, and scanned pages - PLAID indexing for faster, more memory-efficient multi-vector retrieval - New NextPlaid and vLLM Multivector Embeddings components inside Langflow The benchmark results are significant. On long technical reports, text multi-vector retrieval via PLAID reached 94.7 Recall@10, compared to 73.7 with single-vector retrieval. For image retrieval, multi-vector retrieval reached 89.7, compared to 22.6 with a single-vector baseline. If you build RAG workflows over complex documents, technical reports, enterprise knowledge, or visual PDFs, this deep dive is worth reading. 👉 Read the full blog: https://lnkd.in/d98-newT

🚀 Langflow Desktop 1.11 is now available Langflow 1.11 brings new capabilities for building agentic workflows with more control, interoperability, and API-driven execution. This release includes: - Human-in-the-Loop for review and approval gates - A2A protocol support for agent-to-agent interoperability - AG-UI-compatible streaming through the Workflow API If you are already using Langflow Desktop, upgrade in the app to version 1.11. To install Langflow Desktop for the first time, visit: https://lnkd.in/djRBgVNa

🔹 AG-UI streaming for the Workflow API - Langflow 1.11 Bring Langflow workflows into real-time agent interfaces. With the launch of Langflow 1.11, the v2 Workflow API now supports AG-UI-compatible streaming through POST /api/v2/workflows. Developers can run a workflow in stream mode, set stream_protocol: "agui", and receive Server-Sent Events in a format designed for AG-UI clients. Instead of waiting for the full response at the end of a run, external applications can follow the workflow as it executes: - Assistant messages stream as they are generated - Tool activity is surfaced during the run - Workflow steps and state updates are emitted - Completion and error events are sent back to the client The default Langflow EventManager protocol remains available, while AG-UI adds a standard event format for teams building custom agent experiences outside the Langflow canvas. Why it matters: - Makes Langflow easier to integrate into external applications - Enables real-time agent interfaces powered by Langflow workflows - Gives AG-UI clients a compatible streaming format - Helps developers build custom copilots, dashboards, and agent experiences beyond the canvas 👉 Explore AG-UI streaming in Langflow 1.11: https://lnkd.in/dTHiTK9D

A2A protocol support - Langflow 1.11 Connect Langflow flows to broader agent ecosystems. As agentic systems become more distributed, agents need a standard way to discover, call, and collaborate with each other. With the launch of Langflow 1.11, Langflow now supports the Agent2Agent (A2A) protocol, making it possible to publish Langflow flows as callable agents and connect them with other A2A-compatible systems. With A2A support, you can: - Publish Langflow flows as agents that other systems can call - Expose flows through agent discovery and A2A-compatible endpoints - Call remote A2A agents from inside a Langflow flow - Build more modular multi-agent workflows across different environments Example: A Langflow flow can be published as an A2A agent, making it discoverable and callable by external A2A clients. Inside Langflow, you can also use the A2A Agent component to call another published Langflow agent or connect to a remote A2A-compatible agent. This means Langflow can both expose agents to the outside world and call agents from other systems as part of a larger workflow. Why it matters: - Turns Langflow flows into interoperable agents - Makes it easier to connect agentic systems - Supports more flexible multi-agent architectures - Helps developers build workflows where agents collaborate across tools, platforms, and environments 👉 Explore A2A support in Langflow 1.11: https://lnkd.in/dTHiTK9D

🔹 Human-in-the-Loop - Langflow 1.11 Keep humans in control when it matters most. As agentic workflows become more capable, some decisions should not happen automatically. Certain steps may need human review, approval, or a manual choice before the flow continues. With the launch of Langflow 1.11, Human-in-the-Loop lets flows pause execution, create a checkpoint, and wait for a human decision before moving forward. Human-in-the-Loop supports: - Flow pauses at the point where human input is required - Stateful checkpoints before execution continues - Approve, Reject, or custom user choices - Branch-based routing with the Human Input component - Tool approval gates before an agent uses selected tools - Resuming from the checkpoint without rerunning previous steps Example: In this video, the flow receives a user request to search for how many players are currently online playing a game. Before the agent continues, the Human Input component pauses the flow and asks for a human decision: should the search be about Tibia or World of Warcraft? Once the user selects one of the available options, the flow resumes from that checkpoint, follows the selected branch, runs the corresponding web search, and returns the result. This shows how Human-in-the-Loop can turn a fully automated workflow into a controlled decision process, where the agent continues only after the right human input is provided. Why it matters: - Adds control to agentic workflows - Keeps sensitive or important actions under human review - Makes approval and decision flows easier to build visually - Allows workflows to branch based on human input - Keeps agents autonomous while preserving human oversight 👉 Explore Human-in-the-Loop in Langflow 1.11: https://lnkd.in/dTHiTK9D