TheSingleStoreLoader allows you to load documents directly from a SingleStore database table. It is part of thelangchain-singlestore integration package.

Overview​

Integration Details​

Features​

• Load documents lazily to handle large datasets efficiently.
• Supports native asynchronous operations.
• Easily configurable to work with different database schemas.

Setup​

To use theSingleStoreLoader, you need to install thelangchain-singlestore package. Follow the installation instructions below.

Installation​

Installlangchain_singlestore.

%pip install-qU langchain_singlestore

Initialization​

To initializeSingleStoreLoader, you need to provide connection parameters for the SingleStore database and specify the table and fields to load documents from.

Required Parameters:​

• host (str): Hostname, IP address, or URL for the database.
• table_name (str): Name of the table to query. Defaults toembeddings.
• content_field (str): Field containing document content. Defaults tocontent.
• metadata_field (str): Field containing document metadata. Defaults tometadata.

Optional Parameters:​

• id_field (str): Field containing document IDs. Defaults toid.

Connection Pool Parameters:​

• pool_size (int): Number of active connections in the pool. Defaults to5.
• max_overflow (int): Maximum connections beyondpool_size. Defaults to10.
• timeout (float): Connection timeout in seconds. Defaults to30.

Additional Options:​

• pure_python (bool): Enables pure Python mode.
• local_infile (bool): Allows local file uploads.
• charset (str): Character set for string values.
• ssl_key,ssl_cert,ssl_ca (str): Paths to SSL files.
• ssl_disabled (bool): Disables SSL.
• ssl_verify_cert (bool): Verifies server's certificate.
• ssl_verify_identity (bool): Verifies server's identity.
• autocommit (bool): Enables autocommits.
• results_type (str): Structure of query results (e.g.,tuples,dicts).

from langchain_singlestore.document_loadersimport SingleStoreLoader

loader= SingleStoreLoader(
    host="127.0.0.1:3306/db",
    table_name="documents",
    content_field="content",
    metadata_field="metadata",
    id_field="id",
)

Load​

docs= loader.load()
docs[0]

print(docs[0].metadata)

Lazy Load​

page=[]
for docin loader.lazy_load():
    page.append(doc)
iflen(page)>=10:
# do some paged operation, e.g.
# index.upsert(page)

        page=[]

API reference​

For detailed documentation of all SingleStore Document Loader features and configurations head to the github page:https://github.com/singlestore-labs/langchain-singlestore/

Related​

• Document loaderconceptual guide
• Document loaderhow-to guides