mirror of https://github.com/LearningCircuit/local-deep-research.git synced 2026-06-15 19:46:56 +03:00

Files

LearningCircuit d8d982d338 Feature/langchain retriever integration (#502 )

* feat: Add LangChain retriever integration for vector store support

- Add RetrieverRegistry for dynamic retriever registration
- Create RetrieverSearchEngine wrapper for LangChain BaseRetriever
- Integrate retrievers with search factory and config system
- Add retrievers parameter to all API functions
- Include comprehensive test suite and examples
- Support thread-safe operations and multiple retrievers

This allows users to pass any LangChain retriever (FAISS, Pinecone,
Vertex AI, etc.) to LDR and use it as a search engine seamlessly.

* refactor: Organize API examples into structured folders

- Create api_usage/ directory with programmatic/ and http/ subdirectories
- Move existing examples to appropriate folders
- Add comprehensive HTTP API examples (simple and advanced)
- Add curl examples for command-line usage
- Add simple programmatic example for quick start
- Include README explaining when to use each API type

* chore: Remove old example files from root examples directory

Files have been moved to examples/api_usage/programmatic/

* fix: Address PR review comments

- Replace logger.error with logger.exception for better error tracking
- Default retriever name to class name if not provided

2025-06-19 08:44:21 -04:00

2.2 KiB

Raw Blame History

Local Deep Research API Examples

This directory contains examples for using LDR through different interfaces.

Directory Structure

programmatic/ - Direct Python API usage (import from local_deep_research.api)
- programmatic_access.ipynb - Jupyter notebook with comprehensive examples
- retriever_usage_example.py - Using LangChain retrievers with LDR
http/ - HTTP REST API usage (requires running server)
- simple_http_example.py - Quick start example
- http_api_examples.py - Comprehensive examples including batch processing

Quick Start

Programmatic API (Python Package)

from local_deep_research.api import quick_summary

result = quick_summary("What is quantum computing?")
print(result["summary"])

HTTP API (REST)

First, start the server:

python -m src.local_deep_research.web.app

Then use the API:

import requests

response = requests.post(
    "http://localhost:5000/api/v1/quick_summary",
    json={"query": "What is quantum computing?"}
)
print(response.json()["summary"])

Which API Should I Use?

Programmatic API: Use when integrating LDR into your Python application
- ✅ Direct access, no HTTP overhead
- ✅ Full access to all features and parameters
- ✅ Can pass Python objects (like LangChain retrievers)
- ❌ Requires LDR to be installed in your environment
HTTP API: Use when accessing LDR from other languages or remote systems
- ✅ Language agnostic - works with any HTTP client
- ✅ Can run LDR on a separate server
- ✅ Easy to scale and deploy
- ❌ Limited to JSON-serializable parameters
- ❌ Requires running the web server

Running the Examples

Programmatic Examples

# Run the retriever example
python examples/api_usage/programmatic/retriever_usage_example.py

# Or use the Jupyter notebook
jupyter notebook examples/api_usage/programmatic/programmatic_access.ipynb

HTTP Examples

# First, start the LDR server
python -m src.local_deep_research.web.app

# In another terminal, run the examples
python examples/api_usage/http/simple_http_example.py
python examples/api_usage/http/http_api_examples.py

2.2 KiB Raw Blame History