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 #3626] docs(integrations): add PQS (Prompt Quality Score) provider page #3664

New Issue
Open
opened 2026-06-05 18:23:54 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:23:54 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3626
Author: @OnChainAIIntel
Created: 4/17/2026
Status: 🔄 Open

Base: main ← Head: add-pqs-integration-docs

📝 Commits (1)

  • 2794f1e docs(integrations): add PQS (Prompt Quality Score) provider page

📊 Changes

1 file changed (+121 additions, -0 deletions)

View changed files

➕ src/oss/python/integrations/providers/pqs.mdx (+121 -0)

📄 Description

What this adds

Adds a new provider integration doc page at src/oss/python/integrations/providers/pqs.mdx for PQS (Prompt Quality Score) — a pre-inference prompt scoring system that plugs into LangChain via a callback handler.

Style mirrors Langfuse and Helicone — short provider-page format with callback-based integration.

Why this is useful for LangChain users

  • Zero code changes: PQSCallbackHandler plugs into any existing LLM / chain / agent via callbacks=[...]
  • Pre-flight quality gate: optionally raise on low-quality prompts before they burn tokens
  • Framework-native: subclasses BaseCallbackHandler, fires on on_llm_start and on_chat_model_start
  • Zero-signup evaluation: free tier, no account required

Scope of this PR

  • Adds: 1 file — src/oss/python/integrations/providers/pqs.mdx
  • Changes: nothing else
  • No packages.yml entry (PQS ships on PyPI as prompt-quality-score, not a langchain-* partner package; happy to add one if maintainers prefer)

Code examples verified

All code samples in the mdx use the real public SDK surface from pqs_sdk/__init__.py:

from pqs_sdk import PQSCallbackHandler, PQSClient, PQSScoreTool, PQSOptimizeTool

Happy to iterate

If reviewers prefer different positioning, shorter page, or different callback pattern examples, I'll revise. If the LangChain team wants to formalize PQS as a langchain-pqs partner package with its own callback surface in the main monorepo, that's a conversation I'd welcome.

🔄 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/3626 **Author:** [@OnChainAIIntel](https://github.com/OnChainAIIntel) **Created:** 4/17/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-pqs-integration-docs` --- ### 📝 Commits (1) - [`2794f1e`](https://github.com/langchain-ai/docs/commit/2794f1e0697648518c1b55d78994028a15d23481) docs(integrations): add PQS (Prompt Quality Score) provider page ### 📊 Changes **1 file changed** (+121 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/providers/pqs.mdx` (+121 -0) </details> ### 📄 Description ## What this adds Adds a new provider integration doc page at `src/oss/python/integrations/providers/pqs.mdx` for **PQS (Prompt Quality Score)** — a pre-inference prompt scoring system that plugs into LangChain via a callback handler. Style mirrors [Langfuse](https://docs.langchain.com/oss/python/integrations/providers/langfuse) and [Helicone](https://docs.langchain.com/oss/python/integrations/providers/helicone) — short provider-page format with callback-based integration. ## Why this is useful for LangChain users - **Zero code changes**: `PQSCallbackHandler` plugs into any existing LLM / chain / agent via `callbacks=[...]` - **Pre-flight quality gate**: optionally raise on low-quality prompts before they burn tokens - **Framework-native**: subclasses `BaseCallbackHandler`, fires on `on_llm_start` and `on_chat_model_start` - **Zero-signup evaluation**: free tier, no account required ## Scope of this PR - **Adds**: 1 file — `src/oss/python/integrations/providers/pqs.mdx` - **Changes**: nothing else - No `packages.yml` entry (PQS ships on PyPI as `prompt-quality-score`, not a `langchain-*` partner package; happy to add one if maintainers prefer) ## Code examples verified All code samples in the mdx use the real public SDK surface from `pqs_sdk/__init__.py`: ```python from pqs_sdk import PQSCallbackHandler, PQSClient, PQSScoreTool, PQSOptimizeTool ``` ## Happy to iterate If reviewers prefer different positioning, shorter page, or different callback pattern examples, I'll revise. If the LangChain team wants to formalize PQS as a `langchain-pqs` partner package with its own callback surface in the main monorepo, that's a conversation I'd welcome. --- <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 18:23:54 -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#3664
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?