Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

lfx-ibm

IBM components — Db2 Vector Store, watsonx.ai LLM and embeddings, and watsonx.data Presto and MCP — as a standalone Langflow Extension Bundle.

This bundle ships five components:

  • DB2VectorStoreComponent — wraps the DB2VS LangChain-compatible vector store and exposes Db2's native vector search through Langflow's standard vector-store palette entry.
  • WatsonxAIComponent — chat/text-generation against IBM watsonx.ai foundation models via langchain-ibm's ChatWatsonx.
  • WatsonxEmbeddingsComponent — embeddings via watsonx.ai's WatsonxEmbeddings model.
  • WatsonxDataPrestoComponent — run SQL on a watsonx.data Presto engine (Iceberg lakehouse, federated sources, Confluent Tableflow tables) and get a DataFrame back; presto-python-client DBAPI with ibmlhapikey / IAM-API-key or basic auth and an optional CA bundle.
  • WatsonxDataMCPComponent — a preset MCP toolset for the watsonx.data remote MCP server (/api/v2/mcp/): LIST_/QUERY_DOCUMENT_LIBRARY, LIST_/QUERY_DOCUMENT_SET, LIST_/QUERY_DATA_ASSETS for an Agent, with bearer-token or IBM Cloud API-key (IAM exchange) authentication.

It follows the documented porting recipe in src/bundles/PORTING.md.

Install

pip install lfx-ibm

The bundle is registered automatically via the langflow.extensions entry-point. After install, restart your Langflow server; the components appear in the palette under the ibm bundle group.

Platform notes:

  • The ibm-db driver does not ship a prebuilt wheel for linux/aarch64; the dep is gated with a marker so pip install succeeds on that architecture, but DB2VectorStoreComponent will fail to build the vector store at runtime there. Use an x86_64 image or install ibm-db from source if you need Db2 on aarch64.
  • ibm-watsonx-ai (>=1.5.13) and langchain-ibm (>=1.1.0) added Python 3.14 support upstream, so the watsonx components are importable on every supported Python version (3.10-3.14). Earlier releases capped at <3.14; the bundle pins were bumped to pick up the 3.14-capable builds.

Develop

cd src/bundles/ibm
pip install -e .
lfx extension validate src/lfx_ibm

Manifest

The extension manifest is shipped at src/lfx_ibm/extension.json and points at the bundle at components/ibm. Components register under the canonical namespaced IDs:

  • ext:ibm:DB2VectorStoreComponent@official
  • ext:ibm:WatsonxAIComponent@official
  • ext:ibm:WatsonxEmbeddingsComponent@official
  • ext:ibm:WatsonxDataPrestoComponent@official
  • ext:ibm:WatsonxDataMCPComponent@official

Migration

Saved flows referencing the legacy bare class names (DB2VectorStoreComponent, WatsonxAIComponent, WatsonxEmbeddingsComponent) or the old import paths (lfx.components.ibm.<module>.<Class> and the package-level lfx.components.ibm.<Class> forms) are rewritten to the new namespaced IDs by the migration table in src/lfx/src/lfx/extension/migration/migration_table.json.

Metadata

Release files for lfx-ibm 0.2.5rc0

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-ibm 0.2.5rc0
File Interpreter ABI Platform
lfx_ibm-0.2.5rc0-py3-none-any.whl Python 3 none any Details

Release files / lfx_ibm-0.2.5rc0-py3-none-any.whl

Download URL lfx_ibm-0.2.5rc0-py3-none-any.whl
Size 36.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fc74ab5464043c4bf455427d2607ee1342e07d2c09e547e621723d57b20f39dc
BLAKE2b-256 checksum
How to use checksums
64384a3071bb80ccd5a9937fde738fb69cc89d4c7bcf3d21009ea3dc64011955
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}
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