Skip to main content


Sinapsis
Sinapsis Langchain Readers

Load documents and external content through LangChain connectors.

Overview

sinapsis_langchain_readers — Package that provides support for Langchain community data loaders.

A retrieval pipeline must first convert many kinds of sources into documents. This integration isolates source-specific loading from downstream chunking, indexing and embedding.

Where it fits

Choose the extra matching the source you intend to read—web, Wikipedia, PDFs, databases, cloud storage or productivity systems. Provider authentication and parser limitations remain source-specific.

Installation

Requires Python 3.13 or later, as declared in this package’s manifest. Install the base distribution using your preferred package manager:

uv pip install sinapsis_langchain_readers
# or
pip install sinapsis_langchain_readers

Optional features and dependencies

The base installation includes the dependencies required by the package. The following extras are declared in this package’s pyproject.toml; install only those needed by your workflow. They are standard Python optional dependencies, not separate execution profiles.

Extra Adds / when to select it
langchain-webpages-readers LangChain connectors for webpages readers. Dependencies: apify-client, arxiv, beautifulsoup4, browserbase, dgml-utils and 9 more
langchain-wikipedia-readers LangChain connectors for wikipedia readers. Dependencies: wikipedia
langchain-pdfs-readers LangChain connectors for pdfs readers. Dependencies: bibtexparser, pdfplumber, pymupdf, pypdf
langchain-unstructured-readers LangChain connectors for unstructured readers. Dependencies: langchain-unstructured, unstructured[pdf], unstructured-client, python-magic, msoffcrypto-tool
langchain-cloud-readers LangChain connectors for cloud readers. Dependencies: amazon-textract-caller, assemblyai, atlassian-python-api, azure-ai-generative, azure-storage-blob and 16 more
langchain-social-readers LangChain connectors for social readers. Dependencies: langchain-yt-dlp, mastodon-py, nest-asyncio, pandas, telethon and 2 more
langchain-productivity-tools-readers LangChain connectors for productivity tools readers. Dependencies: lxml
langchain-common-readers LangChain connectors for common readers. Dependencies: bs4, jq
langchain-database-readers LangChain connectors for database readers. Dependencies: fauna, langchain, langchain-google-alloydb-pg, motor, pyowm
langchain-productivity-tools LangChain connectors for productivity tools. Dependencies: gitpython
all Bundle declared by this package; its manifest includes langchain-productivity-tools, langchain-database-readers, langchain-common-readers, langchain-productivity-tools-readers, langchain-social-readers, langchain-cloud-readers, langchain-unstructured-readers, langchain-pdfs-readers, langchain-wikipedia-readers, langchain-webpages-readers. It does not include langchain-wepages-readers.
langchain-wepages-readers LangChain connectors for wepages readers. Dependencies: youtube-transcript-api

For example:

uv pip install "sinapsis_langchain_readers[langchain-webpages-readers]"

The manifest also defines development-only dependency groups: dev (ruff, pre-commit). These support source development and testing and are not runtime extras.

🚀 Features

Templates Supported

The Sinapsis Langchain module provides wrapper templates for LangChain's community data loaders, making them seamlessly usable within Sinapsis.

For example, for WikipediaLoaderWrapper use sinx templates example-config WikipediaLoaderWrapper to produce the following example config:

agent:
  name: agent to load Wikipedia documents using WikipediaLoaderWrapper template
templates:
- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}
- template_name: WikipediaLoaderWrapper
  class_name: WikipediaLoaderWrapper
  template_input: InputTemplate
  attributes:
    add_document_as_text_packet: false
    wikipedialoader_init:
        query: the query for wikipedia
        lang: en
        load_max_docs: 5000
        load_all_available_meta: False
        doc_content_chars_max: 4000,

A complete list of available document loader classes in LangChain can be found at: LangChain Community Document Loaders

🚫 Excluded Loaders

Some base classes or loaders that required additional configuration have been excluded and support for this will be included in future releases.

  • Blob
  • BlobLoader
  • OracleTextSplitter
  • OracleDocLoader
  • TrelloLoaderExecute
  • TwitterTweetLoader
  • TrelloLoader
  • GoogleApiYoutubeLoader
  • GoogleApiClient
  • DiscordChatLoader
  • AssemblyAIAudioTranscriptLoader
  • ArcGISLoader

For all other supported loaders, refer to the LangChain API reference linked above.

Example Agent

The following is adapted directly from the package’s shipped one_drive_loader.yml configuration. Save it as my_sinapsis_langchain_readers_agent.yaml. The example may require model checkpoints, input files, additional Template packages, or provider credentials as described in its configuration.

agent:
  name: my_sinapsis_langchain_readers_agent
  description: "One Drive Loader example"

templates:

- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}

- template_name: LangChainOneDriveLoader
  class_name: LangChainOneDriveLoader
  template_input: InputTemplate
  attributes:
    add_document_as_text_packet: false
    folder_id: folder_id
    drive_id: drive_id
    auth_with_token: false
    token_path: /path/to/token.txt
sinx jobs run my_sinapsis_langchain_readers_agent.yaml

More configurations: one_drive_loader.yml, wikipedia_loader.yml, google_drive_loader.yml, test_config.yaml.

Documentation

License

Sinapsis open-source components are available under your choice of the MIT License or the Apache License 2.0, unless otherwise noted.

Metadata

Release files for sinapsis_langchain_readers 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sinapsis_langchain_readers 1.0.0
File Size Uploaded Provenance Actions
sinapsis_langchain_readers-1.0.0.tar.gz 424.3 kB Without provenance Details for sinapsis_langchain_readers-1.0.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sinapsis_langchain_readers 1.0.0
File Interpreter ABI Platform Actions
sinapsis_langchain_readers-1.0.0-py3-none-any.whl Python 3 none any Details for sinapsis_langchain_readers-1.0.0-py3-none-any.whl

Total release size: 448.2 kB

Release files / sinapsis_langchain_readers-1.0.0.tar.gz

Download URL sinapsis_langchain_readers-1.0.0.tar.gz
Size 424.3 kB
Tags Source
SHA-256 checksum
How to use checksums
6b54ce6c1294b56e4c3e6690635a1efdabdee84ec5386700a3ff21e1edcf949e
BLAKE2b-256 checksum
How to use checksums
f7be12901ed001978418af8534cf1a6c44117a91c25761d2a2345add25bf8f81
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.17

Release files / sinapsis_langchain_readers-1.0.0-py3-none-any.whl

Download URL sinapsis_langchain_readers-1.0.0-py3-none-any.whl
Size 23.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
92ff4deb706bf8d73f98b511a39d7d55d2cc81b11a983ece584bf7c86d04d3f4
BLAKE2b-256 checksum
How to use checksums
7c49d3bfc11b16a4bb07aedfe7ca3fc464b5393996361344a1e50fed6d9902f5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.17

Security for sinapsis_langchain_readers 1.0.0

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page