home / skills / orchestra-research / ai-research-skills / qdrant

qdrant skill

safe

This skill helps you implement high-performance vector similarity search for production RAG systems with fast nearest neighbor and flexible filtering.

npx playbooks add skill orchestra-research/ai-research-skills --skill qdrant

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

13.1 KB

---
name: qdrant-vector-search
description: High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed]
dependencies: [qdrant-client>=1.12.0]
---

# Qdrant - Vector Similarity Search Engine

High-performance vector database written in Rust for production RAG and semantic search.

## When to use Qdrant

**Use Qdrant when:**
- Building production RAG systems requiring low latency
- Need hybrid search (vectors + metadata filtering)
- Require horizontal scaling with sharding/replication
- Want on-premise deployment with full data control
- Need multi-vector storage per record (dense + sparse)
- Building real-time recommendation systems

**Key features:**
- **Rust-powered**: Memory-safe, high performance
- **Rich filtering**: Filter by any payload field during search
- **Multiple vectors**: Dense, sparse, multi-dense per point
- **Quantization**: Scalar, product, binary for memory efficiency
- **Distributed**: Raft consensus, sharding, replication
- **REST + gRPC**: Both APIs with full feature parity

**Use alternatives instead:**
- **Chroma**: Simpler setup, embedded use cases
- **FAISS**: Maximum raw speed, research/batch processing
- **Pinecone**: Fully managed, zero ops preferred
- **Weaviate**: GraphQL preference, built-in vectorizers

## Quick start

### Installation

```bash
# Python client
pip install qdrant-client

# Docker (recommended for development)
docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

# Docker with persistent storage
docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrant_storage:/qdrant/storage \
    qdrant/qdrant
```

### Basic usage

```python
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct

# Connect to Qdrant
client = QdrantClient(host="localhost", port=6333)

# Create collection
client.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE)
)

# Insert vectors with payload
client.upsert(
    collection_name="documents",
    points=[
        PointStruct(
            id=1,
            vector=[0.1, 0.2, ...],  # 384-dim vector
            payload={"title": "Doc 1", "category": "tech"}
        ),
        PointStruct(
            id=2,
            vector=[0.3, 0.4, ...],
            payload={"title": "Doc 2", "category": "science"}
        )
    ]
)

# Search with filtering
results = client.search(
    collection_name="documents",
    query_vector=[0.15, 0.25, ...],
    query_filter={
        "must": [{"key": "category", "match": {"value": "tech"}}]
    },
    limit=10
)

for point in results:
    print(f"ID: {point.id}, Score: {point.score}, Payload: {point.payload}")
```

## Core concepts

### Points - Basic data unit

```python
from qdrant_client.models import PointStruct

# Point = ID + Vector(s) + Payload
point = PointStruct(
    id=123,                              # Integer or UUID string
    vector=[0.1, 0.2, 0.3, ...],        # Dense vector
    payload={                            # Arbitrary JSON metadata
        "title": "Document title",
        "category": "tech",
        "timestamp": 1699900000,
        "tags": ["python", "ml"]
    }
)

# Batch upsert (recommended)
client.upsert(
    collection_name="documents",
    points=[point1, point2, point3],
    wait=True  # Wait for indexing
)
```

### Collections - Vector containers

```python
from qdrant_client.models import VectorParams, Distance, HnswConfigDiff

# Create with HNSW configuration
client.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(
        size=384,                        # Vector dimensions
        distance=Distance.COSINE         # COSINE, EUCLID, DOT, MANHATTAN
    ),
    hnsw_config=HnswConfigDiff(
        m=16,                            # Connections per node (default 16)
        ef_construct=100,                # Build-time accuracy (default 100)
        full_scan_threshold=10000        # Switch to brute force below this
    ),
    on_disk_payload=True                 # Store payload on disk
)

# Collection info
info = client.get_collection("documents")
print(f"Points: {info.points_count}, Vectors: {info.vectors_count}")
```

### Distance metrics

| Metric | Use Case | Range |
|--------|----------|-------|
| `COSINE` | Text embeddings, normalized vectors | 0 to 2 |
| `EUCLID` | Spatial data, image features | 0 to ∞ |
| `DOT` | Recommendations, unnormalized | -∞ to ∞ |
| `MANHATTAN` | Sparse features, discrete data | 0 to ∞ |

## Search operations

### Basic search

```python
# Simple nearest neighbor search
results = client.search(
    collection_name="documents",
    query_vector=[0.1, 0.2, ...],
    limit=10,
    with_payload=True,
    with_vectors=False  # Don't return vectors (faster)
)
```

### Filtered search

```python
from qdrant_client.models import Filter, FieldCondition, MatchValue, Range

# Complex filtering
results = client.search(
    collection_name="documents",
    query_vector=query_embedding,
    query_filter=Filter(
        must=[
            FieldCondition(key="category", match=MatchValue(value="tech")),
            FieldCondition(key="timestamp", range=Range(gte=1699000000))
        ],
        must_not=[
            FieldCondition(key="status", match=MatchValue(value="archived"))
        ]
    ),
    limit=10
)

# Shorthand filter syntax
results = client.search(
    collection_name="documents",
    query_vector=query_embedding,
    query_filter={
        "must": [
            {"key": "category", "match": {"value": "tech"}},
            {"key": "price", "range": {"gte": 10, "lte": 100}}
        ]
    },
    limit=10
)
```

### Batch search

```python
from qdrant_client.models import SearchRequest

# Multiple queries in one request
results = client.search_batch(
    collection_name="documents",
    requests=[
        SearchRequest(vector=[0.1, ...], limit=5),
        SearchRequest(vector=[0.2, ...], limit=5, filter={"must": [...]}),
        SearchRequest(vector=[0.3, ...], limit=10)
    ]
)
```

## RAG integration

### With sentence-transformers

```python
from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance, PointStruct

# Initialize
encoder = SentenceTransformer("all-MiniLM-L6-v2")
client = QdrantClient(host="localhost", port=6333)

# Create collection
client.create_collection(
    collection_name="knowledge_base",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE)
)

# Index documents
documents = [
    {"id": 1, "text": "Python is a programming language", "source": "wiki"},
    {"id": 2, "text": "Machine learning uses algorithms", "source": "textbook"},
]

points = [
    PointStruct(
        id=doc["id"],
        vector=encoder.encode(doc["text"]).tolist(),
        payload={"text": doc["text"], "source": doc["source"]}
    )
    for doc in documents
]
client.upsert(collection_name="knowledge_base", points=points)

# RAG retrieval
def retrieve(query: str, top_k: int = 5) -> list[dict]:
    query_vector = encoder.encode(query).tolist()
    results = client.search(
        collection_name="knowledge_base",
        query_vector=query_vector,
        limit=top_k
    )
    return [{"text": r.payload["text"], "score": r.score} for r in results]

# Use in RAG pipeline
context = retrieve("What is Python?")
prompt = f"Context: {context}\n\nQuestion: What is Python?"
```

### With LangChain

```python
from langchain_community.vectorstores import Qdrant
from langchain_community.embeddings import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
vectorstore = Qdrant.from_documents(documents, embeddings, url="http://localhost:6333", collection_name="docs")
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
```

### With LlamaIndex

```python
from llama_index.vector_stores.qdrant import QdrantVectorStore
from llama_index.core import VectorStoreIndex, StorageContext

vector_store = QdrantVectorStore(client=client, collection_name="llama_docs")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)
query_engine = index.as_query_engine()
```

## Multi-vector support

### Named vectors (different embedding models)

```python
from qdrant_client.models import VectorParams, Distance

# Collection with multiple vector types
client.create_collection(
    collection_name="hybrid_search",
    vectors_config={
        "dense": VectorParams(size=384, distance=Distance.COSINE),
        "sparse": VectorParams(size=30000, distance=Distance.DOT)
    }
)

# Insert with named vectors
client.upsert(
    collection_name="hybrid_search",
    points=[
        PointStruct(
            id=1,
            vector={
                "dense": dense_embedding,
                "sparse": sparse_embedding
            },
            payload={"text": "document text"}
        )
    ]
)

# Search specific vector
results = client.search(
    collection_name="hybrid_search",
    query_vector=("dense", query_dense),  # Specify which vector
    limit=10
)
```

### Sparse vectors (BM25, SPLADE)

```python
from qdrant_client.models import SparseVectorParams, SparseIndexParams, SparseVector

# Collection with sparse vectors
client.create_collection(
    collection_name="sparse_search",
    vectors_config={},
    sparse_vectors_config={"text": SparseVectorParams(index=SparseIndexParams(on_disk=False))}
)

# Insert sparse vector
client.upsert(
    collection_name="sparse_search",
    points=[PointStruct(id=1, vector={"text": SparseVector(indices=[1, 5, 100], values=[0.5, 0.8, 0.2])}, payload={"text": "document"})]
)
```

## Quantization (memory optimization)

```python
from qdrant_client.models import ScalarQuantization, ScalarQuantizationConfig, ScalarType

# Scalar quantization (4x memory reduction)
client.create_collection(
    collection_name="quantized",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
    quantization_config=ScalarQuantization(
        scalar=ScalarQuantizationConfig(
            type=ScalarType.INT8,
            quantile=0.99,        # Clip outliers
            always_ram=True      # Keep quantized in RAM
        )
    )
)

# Search with rescoring
results = client.search(
    collection_name="quantized",
    query_vector=query,
    search_params={"quantization": {"rescore": True}},  # Rescore top results
    limit=10
)
```

## Payload indexing

```python
from qdrant_client.models import PayloadSchemaType

# Create payload index for faster filtering
client.create_payload_index(
    collection_name="documents",
    field_name="category",
    field_schema=PayloadSchemaType.KEYWORD
)

client.create_payload_index(
    collection_name="documents",
    field_name="timestamp",
    field_schema=PayloadSchemaType.INTEGER
)

# Index types: KEYWORD, INTEGER, FLOAT, GEO, TEXT (full-text), BOOL
```

## Production deployment

### Qdrant Cloud

```python
from qdrant_client import QdrantClient

# Connect to Qdrant Cloud
client = QdrantClient(
    url="https://your-cluster.cloud.qdrant.io",
    api_key="your-api-key"
)
```

### Performance tuning

```python
# Optimize for search speed (higher recall)
client.update_collection(
    collection_name="documents",
    hnsw_config=HnswConfigDiff(ef_construct=200, m=32)
)

# Optimize for indexing speed (bulk loads)
client.update_collection(
    collection_name="documents",
    optimizer_config={"indexing_threshold": 20000}
)
```

## Best practices

1. **Batch operations** - Use batch upsert/search for efficiency
2. **Payload indexing** - Index fields used in filters
3. **Quantization** - Enable for large collections (>1M vectors)
4. **Sharding** - Use for collections >10M vectors
5. **On-disk storage** - Enable `on_disk_payload` for large payloads
6. **Connection pooling** - Reuse client instances

## Common issues

**Slow search with filters:**
```python
# Create payload index for filtered fields
client.create_payload_index(
    collection_name="docs",
    field_name="category",
    field_schema=PayloadSchemaType.KEYWORD
)
```

**Out of memory:**
```python
# Enable quantization and on-disk storage
client.create_collection(
    collection_name="large_collection",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
    quantization_config=ScalarQuantization(...),
    on_disk_payload=True
)
```

**Connection issues:**
```python
# Use timeout and retry
client = QdrantClient(
    host="localhost",
    port=6333,
    timeout=30,
    prefer_grpc=True  # gRPC for better performance
)
```

## References

- **[Advanced Usage](references/advanced-usage.md)** - Distributed mode, hybrid search, recommendations
- **[Troubleshooting](references/troubleshooting.md)** - Common issues, debugging, performance tuning

## Resources

- **GitHub**: https://github.com/qdrant/qdrant (22k+ stars)
- **Docs**: https://qdrant.tech/documentation/
- **Python Client**: https://github.com/qdrant/qdrant-client
- **Cloud**: https://cloud.qdrant.io
- **Version**: 1.12.0+
- **License**: Apache 2.0

Overview

This skill integrates Qdrant, a Rust-powered high-performance vector similarity search engine, for production RAG and semantic search workflows. It focuses on fast nearest-neighbor search, hybrid vector+metadata filtering, multi-vector support, and scalable deployment with sharding and replication. Use it when you need low latency, on-premise control, or memory-efficient storage for large embedding collections.

How this skill works

The skill exposes Qdrant client patterns: create collections with HNSW or sparse configs, upsert points (id + vector(s) + payload), and run nearest-neighbor searches with optional payload filters. It supports named multi-vector fields, quantization for memory reduction, payload indexing for fast filters, and batch/search-batch APIs for throughput. Both REST and gRPC endpoints are supported for local or cloud deployments.

When to use it

Building production RAG systems requiring low-latency retrieval
Hybrid search combining embeddings with metadata or range filters
Large-scale vector stores needing sharding, replication, or on-disk payloads
Real-time recommendation engines that require fast nearest-neighbor queries
When you need multi-vector records (dense + sparse or multiple embedding models)

Best practices

Batch upsert and batch search to improve throughput and reduce overhead
Index payload fields you use in filters to avoid slow filtered searches
Enable quantization or on-disk payloads for very large collections (>1M vectors)
Tune HNSW params (m, ef_construct, ef_search) for the desired speed/recall tradeoff
Reuse persistent QdrantClient instances and prefer gRPC for lower latency

Example use cases

RAG retrieval pipeline: encode passages, index with payloads, retrieve top-k for prompt context
Hybrid product search: combine dense semantic vectors with price/category filters
Multi-model storage: store embeddings from different encoders as named vectors and query the appropriate one
Real-time recommendations: nearest-neighbor scoring with frequent upserts and low-latency queries
Quantized large index: reduce RAM use with scalar quantization and rescore top results

FAQ

Can Qdrant store multiple embeddings per record?

Yes. Collections can use named vectors so a point can hold multiple embeddings (e.g., 'dense' and 'sparse') and you can search a specific named vector.

How do I keep filtering fast when using metadata?

Create payload indexes for fields used in filters and keep frequently queried fields typed (KEYWORD, INTEGER, FLOAT) to avoid full scans.