langchain-teradata

Teradata Package for LangChain

langchain-teradata is a Teradata package for Langchain that provides users with access to Teradata's Vector Store capabilities.

For community support, please visit the Teradata Community.

For Teradata customer support, please visit Teradata Support.

Copyright 2025, Teradata. All Rights Reserved.

Table of Contents

• Documentation
• Release Notes
• Installation and Requirements
• License

Documentation

General product information, including installation instructions, is available in the Teradata Documentation website.

Release Notes

Version 20.00.00.01

• New features introduced in this release require Database version 20.00.28.XX

• Added a method rename_metadata_keys to rename restricted metadata keys in Langchain Document objects.

• Added support for search_type "mmr" and filters to TeradataVectorStoreRetriever.

• Added support for metadata for input Langchain Document objects.

• Added support for embedding-based Vector Store to TeradataVectorStoreRetriever.

• Added support to delete specific chunks from a file in the vector store using delete_by_ids.

• Added new parameters to pass model url parameters and ingest parameters to from_* and add_* methods during vector store creation:

  • model_urls - Specifies the urls and model information to be used during Vector Store creation.
  • ingest_params - Specifies the parameters to be used for document ingestion for NIM. Applicable only for file-based vector stores.

• Added new parameters for similarity_search:

  • column: Specifies the column name which contains the question in text format.
  • data: Specifies the table name/DataFrame which contains the question in text format.

• Added new parameters for ask:

  • batch_vector_column: Specifies the column that contains the questions in embedded form.
  • question_vector: Specifies the question in vector/embedded form.
  • data: Specifies table name or corresponding teradataml DataFrame where the question is stored (only one question/row should be present).
  • column: Specifies the column name which contains the question in text format.
  • vector_column: Specifies the column name which contains the question in embedded format.

• Added new common parameters for similarity_search, similarity_search_by_vector and ask:

  • top_k: Specifies the number of top similarity matches to be generated.
  • search_threshold: Specifies the threshold value to consider matching tables/views while searching.
  • search_numcluster: Specifies the number of clusters or fraction of train_numcluster to be considered while searching.
  • ef_search: Specifies the number of neighbors to consider during search in HNSW graph.
  • filter: Specifies the filter to be used for filtering the results.
  • filter_style: Specifies whether to apply filtering before or after the similarity_search.
  • maximal_marginal_relevance: Specifies whether to use Maximal Marginal Relevance (MMR) for retrieving documents.
  • lambda_multiplier: Specifies Lambda multiplier to control the trade-off between relevance and diversity when selecting documents.

• Exposed the following classes:

  • ModelUrlParams class to configure model and URL-related parameters for vector store creation using from_* and add_* methods on AI-Factory.
  • IngestParams class to configure ingestor-related parameters for file-based vector store creation using from_* and add_* methods on AI-Factory.
  • Note: Users can still pass these parameters directly while creating the vector store.

• Added the following methods to set the search parameters based on the "search_algorithm":

  • set_kmeans_search_params() method to configure KMEANS search parameters for the vector store.
  • set_hnsw_search_params() method to configure HNSW search parameters for the vector store.
  • set_vectordistance_search_params() method to configure VECTORDISTANCE search algorithm parameters for the vector store.

Version 20.00.00.00

• langchain-teradata 20.00.00.00 marks the first release of the package.

• Features introduced in this release require Database version 20.00.27.XX

• Added methods for managing and creating vector stores:

• from_documents(name, documents, embedding=None, **kwargs): Creates a new vector store, either 'file-based' or 'content-based', depending on the type of input documents. If the input is PDF file(s) or file path(s), a file-based vector store is created. If the input is LangChain Document object(s), a content-based vector store is created. If the store already exists, raises an error.

• from_texts(name, texts, embedding=None, **kwargs): Creates a content-based vector store from raw text or a list of texts. Supports embedding models and chat completion models. If the store already exists, raises an error.

• from_datasets(name, data, embedding=None, **kwargs): Creates a content-based vector store from tables or DataFrames, specifying data columns and optional key columns, with embedding model support. If the store already exists, raises an error.

• from_embeddings(name, data, **kwargs): Creates an embedding-based vector store from pre-embedded tables or DataFrames, specifying the embedding columns. If the store already exists, raises an error.

• add_documents(documents, **kwargs): Adds documents (PDFs, directories, wildcards or Langchain Documents) to an existing vector store. Automatically creates the store if it does not exist.

• add_datasets(data, **kwargs): Adds tables or DataFrames to a content-based vector store. Creates the store if needed.

• add_embeddings(data, **kwargs): Adds embedding data to an embedding-based vector store.

• add_texts(texts, **kwargs): Adds raw text or list of texts to a content-based vector store.

• delete_documents(documents, **kwargs): Removes specified documents from a file-based vector store.

• delete_datasets(data, **kwargs): Removes specified datasets from a content-based vector store.

• delete_embeddings(data, **kwargs): Removes embedding data from an embedding-based vector store.

• similarity_search(question, **kwargs): Performs similarity search in the Vector Store for the input question.

• similarity_search_by_vector(**kwargs): Performs similarity search in the Vector Store for the input question vector or embedded question stored in the input table.

• prepare_response(similarity_results, question, prompt, **kwargs): Prepare a natural language response to the user using the input question and similarity_results provided by similarity_search() method using interactive/batch mode.

• ask(question, prompt, **kwargs): Performs similarity search in the vector store for the input question followed by preparing a natural language response to the user using interactive/batch mode.

• update() : Updates the search parameters of an existing vector store.

• as_retriever(): Creates a TeradataVectorStoreRetriever instance that can be used to retrieve relevant documents.

Installation and Requirements

Package Requirements:

• Python 3.9 or later

Note: 32-bit Python is not supported.

Minimum System Requirements:

• Windows 7 (64Bit) or later
• macOS 10.9 (64Bit) or later
• Red Hat 7 or later versions
• Ubuntu 16.04 or later versions
• CentOS 7 or later versions
• SLES 12 or later versions

Minimum Database Requirements

• Teradata Vantage with database release 20.00.27.XX or later
• Vector Store (Data insights) service is enabled.

Installation

Use pip to install the Teradata Package for Langchain

Platform	Command
macOS/Linux	pip install langchain-teradata
Windows	python -m pip install langchain-teradata

License

Use of the Teradata package for LangChain is governed by the Teradata License Agreement. After installation, the LICENSE.pdf and LICENSE-3RD-PARTY.pdf files are located in the langchain-teradata directory.