IBM

import Icon from "@site/src/components/icon"; import PartialParams from '@site/docs/_partial-hidden-params.mdx'; import PartialConditionalParams from '@site/docs/_partial-conditional-params.mdx'; import PartialVectorSearchResults from '@site/docs/_partial-vector-search-results.mdx'; import PartialVectorStoreInstance from '@site/docs/_partial-vector-store-instance.mdx'; import { GraduatedBundleInstall } from '@site/docs/_partial-bundle-graduated-install.mdx';

<Icon name="Blocks" aria-hidden="true" /> Bundles contain custom components that support specific third-party integrations with Langflow.

The IBM bundle provides access to IBM watsonx.ai models for text and embedding generation, IBM watsonx.data (Presto SQL and the watsonx.data remote MCP server), and an IBM Db2 Vector Store. These components require an IBM watsonx.ai deployment with API credentials, a watsonx.data instance, and/or a reachable IBM Db2 instance with the ibm-db driver.

For IBM Confluent (Kafka, Flink, Tableflow, and the Real-Time Context Engine) — the data-in-motion half of IBM's streaming lakehouse — see the IBM Confluent bundle.

IBM watsonx.ai

The IBM watsonx.ai component generates text using supported foundation models in IBM watsonx.ai. To use gateway models, use the OpenAI text generation component with the gateway model's OpenAI-compatible endpoint.

You can use the IBM watsonx.ai component anywhere you need a language model in a flow.

IBM watsonx.ai parameters {#ibm-watsonxai-parameters}

Name	Type	Description
url	String	Input parameter. The watsonx API base URL for your deployment and region.
project_id	String	Input parameter. Your watsonx Project ID.
api_key	SecretString	Input parameter. A watsonx API key to authenticate watsonx API access to the specified watsonx.ai deployment and model.
model_name	String	Input parameter. The name of the watsonx model to use. Options are dynamically fetched from the API.
max_tokens	Integer	Input parameter. The maximum number of tokens to generate. Default: `1000`.
stop_sequence	String	Input parameter. The sequence where generation should stop.
temperature	Float	Input parameter. Controls randomness in the output. Default: `0.1`.
top_p	Float	Input parameter. Controls nucleus sampling, which limits the model to tokens whose probability is below the `top_p` value. Range: Default: `0.9`.
frequency_penalty	Float	Input parameter. Controls frequency penalty. A positive value decreases the probability of repeating tokens, and a negative value increases the probability. Range: Default: `0.5`.
presence_penalty	Float	Input parameter. Controls presence penalty. A positive value increases the likelihood of new topics being introduced. Default: `0.3`.
seed	Integer	Input parameter. A random seed for the model. Default: `8`.
logprobs	Boolean	Input parameter. Whether to return log probabilities of output tokens or not. Default: `true`.
top_logprobs	Integer	Input parameter. The number of most likely tokens to return at each position. Default: `3`.
logit_bias	String	Input parameter. A JSON string of token IDs to bias or suppress.

IBM watsonx.ai output

The IBM watsonx.ai component can output either a Model Response (Message) or a Language Model (LanguageModel).

Use the Language Model output when you want to use an IBM watsonx.ai model as the LLM for another LLM-driven component, such as an Agent or Smart Transform component. For more information, see Language model components.

The LanguageModel output from the IBM watsonx.ai component is an instance of [ChatWatsonx](https://docs.langchain.com/oss/python/integrations/chat/ibm_watsonx) configured according to the component's parameters.

IBM watsonx.ai Embeddings

The IBM watsonx.ai Embeddings component uses the supported foundation models in IBM watsonx.ai for embedding generation.

The output is Embeddings generated with WatsonxEmbeddings.

For more information about using embedding model components in flows, see Embedding model components.

IBM watsonx.ai Embeddings parameters

Name	Display Name	Info
url	watsonx API Endpoint	Input parameter. The watsonx API base URL for your deployment and region.
project_id	watsonx project id	Input parameter. Your watsonx Project ID.
api_key	API Key	Input parameter. A watsonx API key to authenticate watsonx API access to the specified watsonx.ai deployment and model.
model_name	Model Name	Input parameter. The name of the embedding model to use. Supports default embedding models and automatically updates after connecting to your watsonx.ai deployment.
truncate_input_tokens	Truncate Input Tokens	Input parameter. The maximum number of tokens to process. Default: `200`.
input_text	Include the original text in the output	Input parameter. Determines if the original text is included in the output. Default: `true`.

Default embedding models

By default, the IBM watsonx.ai Embeddings component supports the following default models:

sentence-transformers/all-minilm-l12-v2: 384-dimensional embeddings
ibm/slate-125m-english-rtrvr-v2: 768-dimensional embeddings
ibm/slate-30m-english-rtrvr-v2: 768-dimensional embeddings
intfloat/multilingual-e5-large: 1024-dimensional embeddings

After entering your API endpoint and credentials, the component automatically fetches the list of available models from your watsonx.ai deployment.

IBM Db2 Vector Store

You can use the IBM Db2 Vector Store component to read and write to an IBM Db2 database using an instance of DB2VS vector store. Includes support for remote Db2 instances with enterprise-grade security and performance.

<details> <summary>About vector store instances</summary> <PartialVectorStoreInstance /> </details>

When writing, the component can create a new table at the specified location.

:::tip IBM Db2 Vector Store provides enterprise-grade vector search capabilities with built-in security validation and support for multiple distance strategies. :::

Use the IBM Db2 Vector Store component in a flow

The IBM Db2 Vector Store component can be used for both reads and writes:

When writing, it splits JSON from a URL component into chunks, computes embeddings with attached Embedding Model component, and then loads the chunks and embeddings into the Db2 vector store. To trigger writes, click <Icon name="Play" aria-hidden="true"/> Run component on the IBM Db2 Vector Store component.
When reading, it uses chat input to perform a similarity search on the vector store, and then print the search results to the chat. To trigger reads, open the Playground and enter a chat message.

After running the flow once, you can click <Icon name="TextSearch" aria-hidden="true"/> Inspect Output on each component to understand how the data transformed as it passed from component to component.

IBM Db2 Vector Store parameters

You can inspect a vector store component's parameters to learn more about the inputs it accepts, the features it supports, and how to configure it.

For information about accepted values and functionality, see the provider's documentation or inspect component code.

Name	Type	Description
Table Name (`collection_name`)	String	Input parameter. The name of your Db2 table to store vectors. Default: `LANGFLOW_VECTORS`. The table will be created if it doesn't exist.
Database Name (`database`)	String	Input parameter. Name of the Db2 database. Use a Generic-typed global variable or direct input. Credential-typed variables are not allowed for database names.
Hostname (`hostname`)	String	Input parameter. Db2 server hostname or IP address. Use a Generic-typed global variable or direct input.
Port (`port`)	Integer	Input parameter. Db2 server port. Default: `50000`.
Username (`username`)	String	Input parameter. Db2 database username. Use a Generic-typed global variable or direct input.
Password (`password`)	String	Input parameter. Db2 database password. This should use a Credential-typed global variable for security.
Ingest Data (`ingest_data`)	JSON or Table	Input parameter. `JSON` or `Table` input containing the records to write to the vector store. Only relevant for writes.
Search Query (`search_query`)	String	Input parameter. The query to use for vector search. Only relevant for reads.
Cache Vector Store (`should_cache_vector_store`)	Boolean	Input parameter. If `true`, the component caches the vector store in memory for faster reads. Default: Enabled (`true`).
Embedding (`embedding`)	Embeddings	Input parameter. The embedding function to use for the vector store. You must attach an Embedding Model component to generate embeddings for your data.
Allow Duplicates (`allow_duplicates`)	Boolean	Input parameter. If `true` (default), writes don't check for existing duplicates in the collection, allowing you to store multiple copies of the same content. If `false`, writes won't add documents that match existing documents already present in the collection. Only relevant for writes.
Search Type (`search_type`)	String	Input parameter. The type of search to perform: `Similarity`, `MMR`, or `similarity_score_threshold`. Only relevant for reads.
Number of Results (`number_of_results`)	Integer	Input parameter. The number of search results to return. Default: `4`. Only relevant for reads.
Distance Strategy (`distance_strategy`)	String	Input parameter. Distance calculation strategy: `COSINE`, `EUCLIDEAN_DISTANCE`, or `DOT_PRODUCT`. Default: `COSINE`.

IBM watsonx.data Presto {#ibm-watsonxdata-presto}

The IBM watsonx.data Presto component runs a SQL query on an IBM watsonx.data Presto engine (Java or C++) and returns the rows as a DataFrame. Use it to bring lakehouse data — Iceberg tables, federated sources, and Confluent Tableflow tables registered as an Iceberg REST datasource — into a flow, or expose it to an Agent in Tool Mode so the Agent writes the SQL.

The component uses the Presto DBAPI client (presto-python-client) over HTTPS. On watsonx.data on IBM Cloud, authenticate with api_key: the user name is ibmlhapikey and the password is an IBM Cloud IAM API key. On watsonx.data software, choose basic and provide the user name and password your instance expects, plus the instance CA certificate.

IBM watsonx.data Presto parameters

Name	Type	Description
Presto Host (`host`)	String	Input parameter. Presto engine host name, without `https://`.
Port (`port`)	Integer	Input parameter. Default: `443`.
Catalog (`catalog`)	String	Input parameter. Default catalog for unqualified table names, for example `iceberg_data`.
Schema (`schema_name`)	String	Input parameter. Default schema for unqualified table names.
Authentication (`auth_mode`)	Dropdown	Input parameter. `api_key` (default) or `basic`.
User Name (`username`)	String	Input parameter. Defaults to `ibmlhapikey` for `api_key` authentication.
IBM Cloud API Key (`api_key`)	SecretString	Input parameter. Shown for `api_key` authentication.
Password (`password`)	SecretString	Input parameter. Shown for `basic` authentication.
SQL Query (`query`)	String	Input parameter. Presto SQL to run. Available to Agents in Tool Mode.
Max Rows (`max_rows`)	Integer	Input parameter. Default: `10000`, capped at `1000000`.
Verify SSL Certificate (`verify_ssl`)	Boolean	Input parameter. Default: `true`.
SSL CA Certificate (`ssl_ca_file`)	String	Input parameter. Path or `https` URL of the CA bundle for software instances.
Request Timeout (seconds) (`request_timeout`)	Integer	Input parameter. Default: `60`.
Result Table	DataFrame	Output. Query rows.

IBM watsonx.data MCP {#ibm-watsonxdata-mcp}

The IBM watsonx.data MCP component gives an Agent component governed access to watsonx.data document libraries, document sets, and data assets through the watsonx.data remote MCP server. The server exposes LIST_DOCUMENT_LIBRARY, QUERY_DOCUMENT_LIBRARY, LIST_DOCUMENT_SET, QUERY_DOCUMENT_SET, LIST_DATA_ASSETS, and QUERY_DATA_ASSETS (natural-language queries over selected Presto tables).

The component builds the /api/v2/mcp/ endpoint from the instance URL, authenticates with a bearer token — or exchanges an IBM Cloud API key for one on each connection — and reuses Langflow's MCP client engine. Turn on Tool Mode and connect the Toolset output to an Agent, or pick a Tool and use the Response output directly.

IBM watsonx.data MCP parameters

Name	Type	Description
watsonx.data Instance URL (`instance_url`)	String	Input parameter. Base URL of the instance; `/api/v2/mcp/` is appended automatically.
Authentication (`auth_mode`)	Dropdown	Input parameter. `bearer_token` (default) or `ibm_iam_apikey`.
Bearer Token (`bearer_token`)	SecretString	Input parameter. Access token sent as `Authorization: Bearer`. Shown for `bearer_token`.
IBM Cloud API Key (`api_key`)	SecretString	Input parameter. Exchanged for a token before each connection. Shown for `ibm_iam_apikey`.
IAM Endpoint (`iam_url`)	String	Input parameter. Default: `https://iam.cloud.ibm.com`.
Endpoint Override (`endpoint_override`)	String	Input parameter. Full MCP endpoint URL.
Tool (`tool`)	Dropdown	Input parameter. Tool to run for the Response output; the refresh button re-reads the list from the server.
Tool Arguments (JSON) (`tool_arguments`)	String	Input parameter. JSON object passed as the selected tool's arguments. Ignored in Tool Mode.
Tool Execution Timeout (seconds) (`tool_execution_timeout`)	Float	Input parameter. `0` uses the system-configured MCP timeout.
Verify SSL Certificate (`verify_ssl`)	Boolean	Input parameter. Default: `true`.
Toolset	Tools	Output. Available when Tool Mode is on.
Response	DataFrame	Output. Result of running the selected tool once.

Use other watsonx.data services from Langflow

watsonx.data also ships Milvus and OpenSearch, and existing Langflow components connect to them directly:

Milvus — use the Milvus vector store component with the watsonx.data Milvus service URI and its token.
OpenSearch — use the OpenSearch vector store component with the watsonx.data OpenSearch endpoint.
watsonx.data remote MCP server — the generic MCP Tools component also works: add a server with the URL https://<instance>/api/v2/mcp/ and an Authorization: Bearer <token> header stored in a global variable.