Teradata Package for LangChain Function Reference - prepare_response - Teradata® Package for LangChain - Look here for syntax, methods and examples for the functions included in the Teradata langchain-teradata package.
Teradata® Package for LangChain Function Reference
- Deployment
- VantageCloud
- Edition
- Enterprise
- Product
- Teradata® Package for LangChain
- Release Number
- 20.00.00.01
- Published
- December 2025
- ft:locale
- en-US
- ft:lastEdition
- 2025-12-19
- dita:id
- Langchain-Teradata_FxRef_Lake
- Product Category
- Teradata Vantage
- libs.teradata.langchain_teradata.TeradataVectorStore.prepare_response = prepare_response(self, similarity_results, question=None, prompt=None, **kwargs)
- DESCRIPTION:
Prepare a natural language response to the user using the input
question and similarity_results provided by
VectorStore.similarity_search() method.
The response is generated by a language model configured
in the environment using a pre-configured prompt.
An optional parameter prompt can be used to specify a customized
prompt that replaces the internal prompt.
PARAMETERS:
question:
Required Argument, Optional for batch mode.
Specifies a string of text for which response
needs to be performed.
Types: str
similarity_results:
Required Argument.
Specifies the similarity results obtained by similarity_search().
Types: list
prompt:
Optional Argument.
Specifies a customized prompt that replaces the internal prompt.
Types: str
batch_data:
Required for batch mode.
Specifies the table name or teradataml DataFrame to be indexed for batch mode.
Types: str, teradataml DataFrame
batch_id_column:
Required for batch mode.
Specifies the ID column to be indexed for batch mode.
Types: str
batch_query_column:
Required for batch mode.
Specifies the query column to be indexed for batch mode.
Types: str
temperature:
Optional Argument.
Specifies the temperature for tuning the chat_completion_model.
Types: float, int
Permitted Values: [0.0, 2.0]
RETURNS:
str.
RAISES:
TypeError, TeradataMlException.
EXAMPLES:
# Load necessary imports.
>>> from langchain_teradata import TeradataVectorStore
# Create an instance of a TeradataVectorStore.
>>> vs = TeradataVectorStore.from_texts(name="vs",
texts=["This is a sample text for testing.",
"Another sample text for the vector store.",
"Books talk about the positive user reviews."],
embedding="amazon.titan-embed-text-v1",
top_k=10)
# Perform similarity search in the Vector Store for
# the input question.
>>> question = 'Are there any reviews about books?'
>>> response = vs.similarity_search(question=question)
# Example 1: Prepare a natural language response to the user
# using the input question and similarity_results
# provided by similarity_search().
question='Did any one feel the book is thin?'
similar_objects_list = response['similar_objects_list']
>>> vs.prepare_response(question=question,
similarity_results=similar_objects_list)
# Example 2: Perform batch similarity search in the Vector Store.
# Creates a Vector Store.
# Note this step is not needed if vector store already exists.
>>> vs = TeradataVectorStore.from_datasets(name="vs",
data = "valid_passages",
data_columns = "passage",
key_columns = "pid",
embedding = "amazon.titan-embed-text-v1",
top_k=10,
search_algorithm="HNSW",
vector_column="VectorIndex")
# Perform batch similarity search in the Vector Store.
>>> response = vs.similarity_search(batch_data="valid_passages",
batch_id_column="pid",
batch_query_column="passage")
# Get the similarity results.
from teradatagenai import VSApi
>>> similar_objects_list = vs.get_batch_result(api_name=VSApi.SimilaritySearch)
# Perform batch prepare response with temperature.
>>> vs.prepare_response(similarity_results=similar_objects_list,
batch_data="valid_passages",
batch_id_column="pid",
batch_query_column="passage",
temperature=0.7)
# Retrieve the batch prepare response.
>>> similarity_results = vs.get_batch_result(api_name=VSApi.PrepareResponse)