Skip to main content

nlweb-retrieval

Bundle package containing all retrieval providers for NLWeb.

Included Providers

This package includes clients for:

  • Azure AI Search - Azure's vector search service with managed identity support
  • Elasticsearch - Popular open-source search and analytics engine
  • Milvus - Open-source vector database
  • Qdrant - Vector similarity search engine
  • PostgreSQL (pgvector) - PostgreSQL with vector extension
  • OpenSearch - Open-source search and analytics suite
  • Snowflake Cortex Search - Snowflake's vector search
  • Shopify MCP - Shopify Model Context Protocol
  • Cloudflare AutoRAG - Cloudflare's RAG service
  • Bing Search - Microsoft Bing web search

Installation

pip install nlweb-core nlweb-retrieval

Configuration Example

Create config.yaml:

retrieval:
  provider: elasticsearch
  import_path: nlweb_retrieval.elasticsearch_client
  class_name: ElasticsearchClient
  api_endpoint_env: ELASTICSEARCH_URL
  index_name: my_index
  use_knn: true

Azure AI Search Example

retrieval:
  provider: azure_ai_search
  import_path: nlweb_retrieval.azure_search_client
  class_name: AzureSearchClient
  api_endpoint_env: AZURE_SEARCH_ENDPOINT
  auth_method: azure_ad  # or api_key
  index_name: my-search-index

Qdrant Example

retrieval:
  provider: qdrant
  import_path: nlweb_retrieval.qdrant
  class_name: QdrantVectorClient
  database_path: ./data/qdrant_db  # for local storage
  # OR for remote:
  # api_endpoint_env: QDRANT_URL
  # api_key_env: QDRANT_API_KEY

Usage

import nlweb_core

# Initialize with config
nlweb_core.init(config_path="./config.yaml")

# Use retrieval
from nlweb_core import retriever

# Search
results = await retriever.search(
    query="example query",
    site="example.com",
    num_results=10
)

Provider Import Paths

Use these in your config file:

Provider import_path class_name
Azure AI Search nlweb_retrieval.azure_search_client AzureSearchClient
Elasticsearch nlweb_retrieval.elasticsearch_client ElasticsearchClient
Milvus nlweb_retrieval.milvus_client MilvusVectorClient
Qdrant nlweb_retrieval.qdrant QdrantVectorClient
PostgreSQL nlweb_retrieval.postgres_client PgVectorClient
OpenSearch nlweb_retrieval.opensearch_client OpenSearchClient
Snowflake nlweb_retrieval.snowflake_client SnowflakeCortexSearchClient
Shopify MCP nlweb_retrieval.shopify_mcp ShopifyMCPClient
Cloudflare nlweb_retrieval.cf_autorag_client CloudflareAutoRAGClient
Bing Search nlweb_retrieval.bing_search_client BingSearchClient

License

MIT License - Copyright (c) 2025 Microsoft Corporation

Metadata

Release files for nlweb-retrieval 0.5.3.post1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nlweb-retrieval 0.5.3.post1
File Size Uploaded Provenance Actions
nlweb_retrieval-0.5.3.post1.tar.gz 30.2 kB Without provenance Details for nlweb_retrieval-0.5.3.post1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for nlweb-retrieval 0.5.3.post1
File Interpreter ABI Platform Actions
nlweb_retrieval-0.5.3.post1-py3-none-any.whl Python 3 none any Details for nlweb_retrieval-0.5.3.post1-py3-none-any.whl

Total release size: 69.0 kB

Release files / nlweb_retrieval-0.5.3.post1.tar.gz

Download URL nlweb_retrieval-0.5.3.post1.tar.gz
Size 30.2 kB
Tags Source
SHA-256 checksum
How to use checksums
656c0d76fc68b8b337b2561b33d38ea3d165976e05267de12b65ce431ea091f3
BLAKE2b-256 checksum
How to use checksums
63e5d7aa77ca515b7d7493b93b5ab1df541168bf9241738eb6c421bb2e468b3f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.7

Release files / nlweb_retrieval-0.5.3.post1-py3-none-any.whl

Download URL nlweb_retrieval-0.5.3.post1-py3-none-any.whl
Size 38.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
97eb71386208d63a449df749e45867093ef92a5f9dfd9c7cde3621389aee3c59
BLAKE2b-256 checksum
How to use checksums
77026012183bf1d8c72636fb5ec293b0fa6826058431c3921244487e774dc503
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.7

Security for nlweb-retrieval 0.5.3.post1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page