Issue Station
Sign In
Tools hereToolbox

langchain - ✅(Solved) Fix partners[agentdb]: add langchain-agentdb retriever package [1 pull requests, 2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
langchain-ai/langchain#36883•Fetched 2026-04-20 11:58:59
View on GitHub
Comments
2
Participants
2
Timeline
7
Reactions
0
Author
AgentBC9000AgentBC9000
Participants
AgentBC9000AgentBC9000mdrxymdrxy
Timeline (top)
commented ×2labeled ×2closed ×1cross-referenced ×1

Proposing a new partner integration for AgentDB — a real-time curated knowledge API for AI agents (https://agentdb.dev).

AgentDB ingests YouTube channels, podcasts, and blogs on a Mon/Wed/Fri schedule, summarises each item with Claude, and exposes structured knowledge via REST API with optional semantic vector search.

Root Cause

Proposing a new partner integration for AgentDB — a real-time curated knowledge API for AI agents (https://agentdb.dev).

AgentDB ingests YouTube channels, podcasts, and blogs on a Mon/Wed/Fri schedule, summarises each item with Claude, and exposes structured knowledge via REST API with optional semantic vector search.

Fix Action

Fixed

PR fix notes

PR #36884: partners[agentdb]: add langchain-agentdb retriever package

Description (problem / solution / changelog)

Closes #36883 Adds a new partner integration for AgentDB — a real-time curated knowledge API for AI agents.

  • AgentDBRetriever with mode="search" (semantic vector) and mode="latest"
  • Full sync + async support via httpx
  • Filters: content_type, tags, min_confidence
  • 21 unit tests (zero live network calls), integration test stubs
  • pyproject.toml, README, Makefile following partner package conventions

AgentDB ingests YouTube, podcasts, and blogs Mon/Wed/Fri and summarises with Claude. Free tier: 100 req/day. Sign up at https://agentdb.dev

Fixes #

<!-- Replace everything above this line with a 1-2 sentence description of your change. Keep the "Fixes #xx" keyword and update the issue number. -->

Read the full contributing guidelines: https://docs.langchain.com/oss/python/contributing/overview

All contributions must be in English. See the language policy.

If you paste a large clearly AI generated description here your PR may be IGNORED or CLOSED!

Thank you for contributing to LangChain! Follow these steps to have your pull request considered as ready for review.

  1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
  1. PR description:
  • Write 1-2 sentences summarizing the change.
  • The Fixes #xx line at the top is required for external contributions — update the issue number and keep the keyword. This links your PR to the approved issue and auto-closes it on merge.
  • If there are any breaking changes, please clearly describe them.
  • If this PR depends on another PR being merged first, please include "Depends on #PR_NUMBER" in the description.
  1. Run make format, make lint and make test from the root of the package(s) you've modified.
  • We will not consider a PR unless these three are passing in CI.
  1. How did you verify your code works?

Additional guidelines:

  • All external PRs must link to an issue or discussion where a solution has been approved by a maintainer, and you must be assigned to that issue. PRs without prior approval will be closed.
  • PRs should not touch more than one package unless absolutely necessary.
  • Do not update the uv.lock files or add dependencies to pyproject.toml files (even optional ones) unless you have explicit permission to do so by a maintainer.

Social handles (optional)

<!-- If you'd like a shoutout on release, add your socials below -->

Twitter: @ LinkedIn: https://linkedin.com/in/

Changed files

  • libs/partners/agentdb/Makefile (added, +69/-0)
  • libs/partners/agentdb/README.md (added, +74/-0)
  • libs/partners/agentdb/langchain_agentdb/__init__.py (added, +7/-0)
  • libs/partners/agentdb/langchain_agentdb/py.typed (added, +0/-0)
  • libs/partners/agentdb/langchain_agentdb/retrievers.py (added, +239/-0)
  • libs/partners/agentdb/pyproject.toml (added, +103/-0)
  • libs/partners/agentdb/tests/__init__.py (added, +0/-0)
  • libs/partners/agentdb/tests/integration_tests/__init__.py (added, +0/-0)
  • libs/partners/agentdb/tests/integration_tests/test_retrievers.py (added, +24/-0)
  • libs/partners/agentdb/tests/unit_tests/__init__.py (added, +0/-0)
  • libs/partners/agentdb/tests/unit_tests/test_imports.py (added, +12/-0)
  • libs/partners/agentdb/tests/unit_tests/test_retrievers.py (added, +270/-0)

Code Example

from langchain_agentdb import AgentDBRetriever

retriever = AgentDBRetriever(mode="search", k=10)
docs = retriever.invoke("AI safety developments this week")

### Use Case

AI agents built with LangChain have no built-in way to access current, real-world knowledge without making expensive web search calls on every query. This means agents either work with stale training data or burn API budget on search tools that return noisy, unstructured results.

AgentDB solves this by acting as a continuously-updated knowledge feed — ingesting YouTube channels, podcasts, and blogs on a Mon/Wed/Fri schedule, summarising each item with Claude, and returning clean structured JSON. A LangChain agent using AgentDBRetriever can ask "what happened in AI this week" and get back pre-summarised, tagged, confidence-scored documents instantly — no scraping, no parsing, no prompt engineering around noisy HTML.

The primary users are developers building research assistants, daily briefing agents, market monitoring tools, and any agent that needs to stay current without a live internet connection on every run.

### Proposed Solution

Add a new partner package `langchain-agentdb` under `libs/partners/agentdb/` following the same conventions as existing partners (exa, perplexity, etc.).

The package would expose a single `AgentDBRetriever` class with:

- `mode="search"` — semantic vector search via the AgentDB API
- `mode="latest"` — fetch newest items with optional filters (content_type, tags, min_confidence)
- Full sync + async support via httpx

### Alternatives Considered

Developers currently work around this by using Tavily or Perplexity for live web search, but these are expensive per-query and return unstructured HTML that requires additional parsing. AgentDB is complementary — it's a pre-summarised, structured knowledge feed rather than an ad-hoc search tool, so agents can use both depending on the task.

### Additional Context

The integration is fully built and ready for review:

- Repo: https://github.com/AgentBC9000/agentdb
- Fork with PR-ready code: https://github.com/AgentBC9000/langchain/tree/master/libs/partners/agentdb

Example usage:
RAW_BUFFERClick to expand / collapse

Submission checklist

  • This is a feature request, not a bug report or usage question.
  • I added a clear and descriptive title that summarizes the feature request.
  • I used the GitHub search to find a similar feature request and didn't find it.
  • I checked the LangChain documentation and API reference to see if this feature already exists.
  • This is not related to the langchain-community package.

Package (Required)

  • langchain
  • langchain-openai
  • langchain-anthropic
  • langchain-classic
  • langchain-core
  • langchain-model-profiles
  • langchain-tests
  • langchain-text-splitters
  • langchain-chroma
  • langchain-deepseek
  • langchain-exa
  • langchain-fireworks
  • langchain-groq
  • langchain-huggingface
  • langchain-mistralai
  • langchain-nomic
  • langchain-ollama
  • langchain-openrouter
  • langchain-perplexity
  • langchain-qdrant
  • langchain-xai
  • Other / not sure / general

Feature Description

Summary

Proposing a new partner integration for AgentDB — a real-time curated knowledge API for AI agents (https://agentdb.dev).

AgentDB ingests YouTube channels, podcasts, and blogs on a Mon/Wed/Fri schedule, summarises each item with Claude, and exposes structured knowledge via REST API with optional semantic vector search.

What this adds

A new package langchain-agentdb under libs/partners/agentdb/ containing:

  • AgentDBRetriever with two modes:
    • mode="search" — semantic vector search (Pro tier)
    • mode="latest" — newest items with optional filters (free tier)
  • Full sync + async support via httpx
  • Filters: content_type, tags, min_confidence
  • 21 unit tests, zero live network calls
  • Free tier: 100 req/day at https://agentdb.dev

Motivation

AI agents need access to current, structured knowledge without scraping the web. AgentDB solves this by continuously ingesting and summarising curated sources — a natural retriever for LangChain agents that need up-to-date context.

Example

from langchain_agentdb import AgentDBRetriever

retriever = AgentDBRetriever(mode="search", k=10)
docs = retriever.invoke("AI safety developments this week")

### Use Case

AI agents built with LangChain have no built-in way to access current, real-world knowledge without making expensive web search calls on every query. This means agents either work with stale training data or burn API budget on search tools that return noisy, unstructured results.

AgentDB solves this by acting as a continuously-updated knowledge feed — ingesting YouTube channels, podcasts, and blogs on a Mon/Wed/Fri schedule, summarising each item with Claude, and returning clean structured JSON. A LangChain agent using AgentDBRetriever can ask "what happened in AI this week" and get back pre-summarised, tagged, confidence-scored documents instantly — no scraping, no parsing, no prompt engineering around noisy HTML.

The primary users are developers building research assistants, daily briefing agents, market monitoring tools, and any agent that needs to stay current without a live internet connection on every run.

### Proposed Solution

Add a new partner package `langchain-agentdb` under `libs/partners/agentdb/` following the same conventions as existing partners (exa, perplexity, etc.).

The package would expose a single `AgentDBRetriever` class with:

- `mode="search"` — semantic vector search via the AgentDB API
- `mode="latest"` — fetch newest items with optional filters (content_type, tags, min_confidence)
- Full sync + async support via httpx

### Alternatives Considered

Developers currently work around this by using Tavily or Perplexity for live web search, but these are expensive per-query and return unstructured HTML that requires additional parsing. AgentDB is complementary — it's a pre-summarised, structured knowledge feed rather than an ad-hoc search tool, so agents can use both depending on the task.

### Additional Context

The integration is fully built and ready for review:

- Repo: https://github.com/AgentBC9000/agentdb
- Fork with PR-ready code: https://github.com/AgentBC9000/langchain/tree/master/libs/partners/agentdb

Example usage:

```python
from langchain_agentdb import AgentDBRetriever

# Semantic search
retriever = AgentDBRetriever(mode="search", k=10)
docs = retriever.invoke("AI safety developments this week")

# Latest items filtered by type
retriever = AgentDBRetriever(mode="latest", content_type="podcast", k=20)
docs = retriever.invoke("")

extent analysis

TL;DR

The proposed solution is to add a new partner package langchain-agentdb to integrate AgentDB's real-time curated knowledge API into LangChain.

Guidance

  • Review the provided code in the forked repository (https://github.com/AgentBC9000/langchain/tree/master/libs/partners/agentdb) to ensure it meets LangChain's conventions and standards.
  • Verify the AgentDBRetriever class works as expected in both mode="search" and mode="latest" with various filters and parameters.
  • Consider the potential impact of adding a new dependency on the LangChain ecosystem and its users, particularly regarding the 100 req/day limit on the free tier of AgentDB.
  • Evaluate the benefits of using AgentDB as a complementary knowledge feed alongside other search tools like Tavily or Perplexity.

Example

from langchain_agentdb import AgentDBRetriever

# Example usage of semantic search
retriever = AgentDBRetriever(mode="search", k=10)
docs = retriever.invoke("AI safety developments this week")

# Example usage of latest items with filters
retriever = AgentDBRetriever(mode="latest", content_type="podcast", k=20)
docs = retriever.invoke("")

Notes

The integration is fully built and ready for review, but it's essential to consider the potential limitations and implications of adding a new package to the LangChain ecosystem.

Recommendation

Apply the proposed solution by adding the langchain-agentdb package, as it provides a valuable complementary knowledge feed for LangChain agents, but be aware of the potential limitations and dependencies.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#GPU setup#container setup#orchestration issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING