langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-21 20:05:30 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #2804] docs: add veritensor.mdx #2901

New Issue
Open
opened 2026-06-05 18:20:21 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:20:21 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/2804
Author: @arsbr
Created: 2/25/2026
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (1)

📊 Changes

1 file changed (+49 additions, -0 deletions)

View changed files

➕ src/oss/python/integrations/providers/veritensor.mdx (+49 -0)

📄 Description

Overview

This PR adds documentation for Veritensor, an open-source AI security tool that provides a wrapper for LangChain Document Loaders (SecureLangChainLoader).

Following our recent addition to the official awesome-langchain list under the "Services" section, we wanted to provide clear, official documentation on how LangChain users can implement this security layer.

As RAG pipelines increasingly ingest untrusted or user-generated documents (PDFs, web scrapes), they become vulnerable to indirect prompt injections and data poisoning (e.g., hidden text via CSS). This integration allows developers to sanitize documents locally before they are passed to text splitters and vector stores, preventing malicious payloads from compromising the LLM.

Type of change

  • New documentation page

Related issues/PRs

  • Feature PR: N/A

Checklist

  • I have read the contributing guidelines
  • I have tested my changes locally using docs dev
  • All code examples have been tested and work correctly
  • I have used root relative paths for internal links
  • I have updated navigation in src/docs.json if needed

Additional notes

The added documentation (src/oss/python/integrations/providers/veritensor.mdx) includes installation instructions and a code example demonstrating how to wrap a PyPDFLoader to block prompt injections, stealth attacks, and PII leaks during RAG data ingestion.
I intentionally left src/docs.json untouched. I wasn't entirely sure which specific group/section would be the most appropriate place for Veritensor in your current sidebar structure (e.g., Document Loaders vs. Security integrations).
Could you please advise on where it should go, or help link it in the navigation during the merge? Thank you!

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/2804 **Author:** [@arsbr](https://github.com/arsbr) **Created:** 2/25/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`551b018`](https://github.com/langchain-ai/docs/commit/551b018a9055570aeb52aa566583261818df9132) Create veritensor.mdx ### 📊 Changes **1 file changed** (+49 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/providers/veritensor.mdx` (+49 -0) </details> ### 📄 Description ## Overview This PR adds documentation for `Veritensor`, an open-source AI security tool that provides a wrapper for LangChain Document Loaders (`SecureLangChainLoader`). Following our recent addition to the official [awesome-langchain](https://github.com/kyrolabs/awesome-langchain) list under the "Services" section, we wanted to provide clear, official documentation on how LangChain users can implement this security layer. As RAG pipelines increasingly ingest untrusted or user-generated documents (PDFs, web scrapes), they become vulnerable to indirect prompt injections and data poisoning (e.g., hidden text via CSS). This integration allows developers to sanitize documents locally *before* they are passed to text splitters and vector stores, preventing malicious payloads from compromising the LLM. ## Type of change - [x] New documentation page ## Related issues/PRs - Feature PR: N/A ## Checklist - [x] I have read the [contributing guidelines](README.md) - [ ] I have tested my changes locally using `docs dev` - [x] All code examples have been tested and work correctly - [x] I have used **root relative** paths for internal links - [ ] I have updated navigation in `src/docs.json` if needed ## Additional notes The added documentation (`src/oss/python/integrations/providers/veritensor.mdx`) includes installation instructions and a code example demonstrating how to wrap a `PyPDFLoader` to block prompt injections, stealth attacks, and PII leaks during RAG data ingestion. I intentionally left `src/docs.json` untouched. I wasn't entirely sure which specific group/section would be the most appropriate place for Veritensor in your current sidebar structure (e.g., Document Loaders vs. Security integrations). Could you please advise on where it should go, or help link it in the navigation during the merge? Thank you! --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:20:21 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#2901
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?