Qdrant RAG Plugin
Hybrid search RAG (Retrieval Augmented Generation) using Qdrant's built-in fastembed integration for dense and BM25 sparse embeddings.
Features
- Hybrid Search: Dense vector (semantic) + BM25 sparse (keyword) via native Qdrant RRF fusion
- fastembed Native: No external embedding dependencies — Qdrant client handles everything
- Implements RAG Interface: Compatible with Vision Agents RAG base class
Installation
uv add "vision-agents[qdrant]"
# or directly
uv add vision-agents-plugins-qdrant
Usage
from vision_agents.plugins import qdrant
# Initialize RAG (connects to local Qdrant by default)
rag = qdrant.QdrantRAG(collection="my-knowledge")
await rag.add_directory("./knowledge")
# Hybrid search (default)
results = await rag.search("How does the chat API work?")
# Vector-only search
results = await rag.search("How does the chat API work?", mode="vector")
# BM25 search
results = await rag.search("chat API pricing", mode="bm25")
# Or use convenience function
rag = await qdrant.create_rag(
collection="product-knowledge",
knowledge_dir="./knowledge"
)
Configuration
| Parameter | Description | Default |
|---|---|---|
collection |
Qdrant collection name | Required |
url |
Qdrant server URL | http://localhost:6333 |
api_key |
Qdrant API key (for Qdrant Cloud) | QDRANT_API_KEY env var |
dense_model |
fastembed dense model for semantic search | sentence-transformers/all-MiniLM-L6-v2 |
sparse_model |
fastembed sparse model for BM25 search | Qdrant/bm25 |
chunk_size |
Size of text chunks for splitting documents | 10000 |
chunk_overlap |
Overlap between chunks for context continuity | 200 |
cloud_inference |
Use Qdrant Cloud server-side inference instead of local fastembed | False |
Environment Variables
QDRANT_API_KEY: Qdrant API key (for Qdrant Cloud; not needed for local)
Running Qdrant locally
docker run -p 6333:6333 qdrant/qdrant
Dependencies
qdrant-client[fastembed]: Qdrant async client with built-in fastembed supportlangchain-text-splitters: Text chunking utilities
References
Metadata
Release files for vision-agents-plugins-qdrant 0.6.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vision_agents_plugins_qdrant-0.6.9.tar.gz | 4.6 kB | Without provenance | Details for vision_agents_plugins_qdrant-0.6.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vision_agents_plugins_qdrant-0.6.9-py3-none-any.whl | Python 3 | none | any | Details for vision_agents_plugins_qdrant-0.6.9-py3-none-any.whl |
Total release size: 9.6 kB
Release files / vision_agents_plugins_qdrant-0.6.9.tar.gz
| Download URL | vision_agents_plugins_qdrant-0.6.9.tar.gz |
|---|---|
| Size | 4.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9452dda56f0153e7d4fc2fa01fef7eeb8c679b7c9a59a5f8336172c02f9c47de
|
|
BLAKE2b-256 checksum How to use checksums |
75354aa36ac287f67b7c4043754e5d369310efec8a3306cc5db87258e102f67e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / vision_agents_plugins_qdrant-0.6.9-py3-none-any.whl
| Download URL | vision_agents_plugins_qdrant-0.6.9-py3-none-any.whl |
|---|---|
| Size | 4.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3ae4e7825249baacde7c5f0caed47fde899f622d5b07776f6be032e5e4d448be
|
|
BLAKE2b-256 checksum How to use checksums |
7d055933b73f654b7e580e713e6434810e290f24e6e18ec243a84e659d34c518
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for vision-agents-plugins-qdrant 0.6.9
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.