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 theDB2VSLangChain-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 vialangchain-ibm'sChatWatsonx.WatsonxEmbeddingsComponent— embeddings via watsonx.ai'sWatsonxEmbeddingsmodel.WatsonxDataPrestoComponent— run SQL on a watsonx.data Presto engine (Iceberg lakehouse, federated sources, Confluent Tableflow tables) and get a DataFrame back;presto-python-clientDBAPI withibmlhapikey/ 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_ASSETSfor 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-dbdriver does not ship a prebuilt wheel forlinux/aarch64; the dep is gated with a marker sopip installsucceeds on that architecture, butDB2VectorStoreComponentwill fail to build the vector store at runtime there. Use an x86_64 image or installibm-dbfrom source if you need Db2 on aarch64.ibm-watsonx-ai(>=1.5.13) andlangchain-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@officialext:ibm:WatsonxAIComponent@officialext:ibm:WatsonxEmbeddingsComponent@officialext:ibm:WatsonxDataPrestoComponent@officialext: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 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| lfx_ibm-0.3.1-py3-none-any.whl | Python 3 | none | any | Details for lfx_ibm-0.3.1-py3-none-any.whl |
Release files / lfx_ibm-0.3.1-py3-none-any.whl
| Download URL | lfx_ibm-0.3.1-py3-none-any.whl |
|---|---|
| Size | 37.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
08f0989337b545aae13a985c6857d891264e47d0ef9886ae4aacbda577315d5c
|
|
BLAKE2b-256 checksum How to use checksums |
156f2ef4f14774c1ce48498433db3c0d808afde37ed7b8281dba742ba3f386b6
|
| 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}
|
Security for lfx-ibm 0.3.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.