Skip to main content

lfx-confluent

IBM Confluent — the data-in-motion half of IBM's streaming lakehouse — as a standalone Langflow Extension Bundle. Everything talks to Confluent over open protocols only (Kafka wire protocol, the Tableflow Iceberg REST catalog, and MCP over Streamable HTTP), so the same components work against Confluent Cloud, Confluent Platform, and WarpStream wherever the corresponding surface is exposed.

What it ships

Four components, registered under the confluent bundle group:

  • Confluent Real-Time Context Engine (ConfluentContextEngineComponent, canonical ID ext:confluent:ConfluentContextEngineComponent@official) — a preset MCP toolset for Confluent's Real-Time Context Engine. Templates the regional MCP endpoint from your organization / environment / cluster IDs, authenticates with a Confluent Cloud API key, and exposes list_topics, get_metadata, and query_data to an Agent (Tool Mode) or runs one tool directly (Response output).
  • Confluent Kafka Producer (ConfluentKafkaProducerComponent) — publish a Message, a Data object, or every row of a DataFrame to a topic and return the delivery report.
  • Confluent Kafka Consumer (ConfluentKafkaConsumerComponent) — read a bounded batch of records (message limit + timeout) into a DataFrame; JSON, string, Avro, and JSON-Schema (Schema Registry) values.
  • Confluent Tableflow Reader (ConfluentTableflowReaderComponent) — read a Kafka topic that Tableflow has materialized as an Apache Iceberg table through the Tableflow Iceberg REST catalog (pyiceberg, no JVM), with a row filter, projection, and row limit; or list the tables in a cluster.

Built on confluent-kafka and pyiceberg; the MCP component reuses Langflow's own MCP client engine.

Install

pip install lfx-confluent

pip install "langflow[bundles]" also includes it.

Develop

The bundle is a uv workspace member of the Langflow monorepo:

uv sync
uv run pytest src/bundles/confluent/tests -q
uv run lfx extension validate src/bundles/confluent/src/lfx_confluent

To iterate on the components with a live palette:

uv run lfx extension dev src/bundles/confluent

Live smoke tests (marked api_key_required) need a Confluent Cloud environment; see the test module docstrings for the environment variables they read.

Metadata

Release files for lfx-confluent 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for lfx-confluent 0.1.0
File Interpreter ABI Platform
lfx_confluent-0.1.0-py3-none-any.whl Python 3 none any Details

Release files / lfx_confluent-0.1.0-py3-none-any.whl

Download URL lfx_confluent-0.1.0-py3-none-any.whl
Size 20.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ed21594ecfca6ed8ccfd5f4935ef881d0cb8b1857cfc3bf0d8aec046a34e4068
BLAKE2b-256 checksum
How to use checksums
99f6c1446b93f693e1caab5b66adcaa5db37316e4506bd27dfb3a49bbda9ff20
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release history Release notifications | RSS feed

This release

0.1.0 This release

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page