Skip to content

Add AI Cordon Picket integration - #576

Open
mihail-gribov wants to merge 1 commit into
deepset-ai:mainfrom
mihail-gribov:add-aicordon-haystack
Open

Add AI Cordon Picket integration#576
mihail-gribov wants to merge 1 commit into
deepset-ai:mainfrom
mihail-gribov:add-aicordon-haystack

Conversation

@mihail-gribov

Copy link
Copy Markdown

Two Haystack components from aicordon-haystack, one for each place a pipeline holds text a model is about to read:

  • PromptInjectionFilter (preprocessors) checks documents at ingest, before chunking and embedding;
  • PromptInjectionGuard (validators) checks the message list on its way into the generator, and routes a flagged exchange to a blocked socket instead of calling the model.

The check is a local rule base - no GPU, no network, no API key, no dependencies beyond aicordon. Measured on the pipeline rather than on the detector, with the numbers and the harness in the package README.

Card follows the schema in this repo's README: one card per package, pypi and repo both resolve.

@mihail-gribov
mihail-gribov requested a review from a team as a code owner August 21, 2026 21:40
@vercel

vercel Bot commented Aug 21, 2026

Copy link
Copy Markdown

@mihail-gribov is attempting to deploy a commit to the deepset Team on Vercel.

A member of the Team first needs to authorize it.

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🟡 Changes recommended

The integration page sets toc: true but is missing the repository’s standard “Table of Contents” block, making it inconsistent with the documented integration template.

Once you've addressed the issues Copilot identified, you can request another Copilot review.

Pull request overview
  • Adds a new integration card for the aicordon-haystack package, documenting two Haystack components intended to detect prompt injection at ingest-time and pre-generation time.

Changes:

  • Adds installation instructions and usage examples for PromptInjectionFilter (ingest/documents) and PromptInjectionGuard (generator/messages).
  • Documents routing behavior (blocked socket) and includes benchmark/latency figures plus license details.
File summaries
File Description
integrations/aicordon-haystack.md New integration documentation page for AI Cordon Picket components, including usage patterns, measured results, and license.
Review details
  • Files reviewed: 1/1 changed files
  • Comments generated: 1
  • Review effort level: Lite

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment on lines +19 to +20
Check what an LLM is given for prompt injection - in both places it can arrive.

socials:
github: mihail-gribov
pypi: https://pypi.org/project/aicordon-haystack
repo: https://github.com/AICordon/aicordon

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
repo: https://github.com/AICordon/aicordon
repo: https://github.com/AICordon/aicordon/tree/main/integrations/haystack

We typically link the integration itself, not the main repository.

Comment on lines +23 to +24
| `PromptInjectionFilter` | **material**: documents at ingest, before they are chunked and embedded | Picket's `ipi` rules |
| `PromptInjectionGuard` | **the request**: the turn the model is about to answer | Picket's `dpi` rules |

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you please define the Picket's rules? It might be unclear.

Comment on lines +30 to +31
The check is a rule, not a model: no GPU, no network, no key, a few hundred kilobytes of base, and a
fraction of a millisecond per turn on one core.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we elaborate on the algorithm used by aicordon? Since it is supposed to intercept the communication with the LLM, that might be crucial for our users to understand if that's safe enough.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants