Qdrant Vector Search Engine: Production RAG with Hermes Agent

Qdrant is a high-performance vector database written in Rust, designed for production RAG systems and semantic search. This guide covers how to use Qdrant within Hermes Agent, from setup through advanced features like multi-vector support and quantization, with code examples for each operation.

What it does

Qdrant stores and retrieves vector embeddings alongside arbitrary JSON metadata. You feed it vectors (from any embedding model) and it returns the nearest neighbors, optionally filtered by payload fields. It is built for low-latency queries at scale, with horizontal scaling via sharding and replication, and supports dense, sparse, and multi-vector per point. You can run it on-premise or connect to Qdrant Cloud.

Before you start

This skill is optional and installed on demand. It requires:

• Python with pip
• Docker (for local Qdrant server)
• A running Qdrant instance (local or cloud)
• The qdrant-client Python package

Platforms: Linux, macOS, Windows.

Install the client:

# 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

Connect to Qdrant, create a collection, insert vectors with payload, and search with filtering.

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 (query_points is the current API; client.search is removed in qdrant-client 1.14+)
response = client.query_points(
    collection_name="documents",
    query=[0.15, 0.25, ...],
    query_filter={
        "must": [{"key": "category", "match": {"value": "tech"}}]
    },
    limit=10
)

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

Core concepts

Points - Basic data unit

A point is the fundamental unit: an ID, one or more vectors, and a JSON payload.

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

Collections hold points and define vector configuration, distance metric, and HNSW parameters.

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

# Simple nearest neighbor search (returns a QueryResponse; use .points)
response = client.query_points(
    collection_name="documents",
    query=[0.1, 0.2, ...],
    limit=10,
    with_payload=True,
    with_vectors=False  # Don't return vectors (faster)
)
results = response.points

Filtered search

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

# Complex filtering
response = client.query_points(
    collection_name="documents",
    query=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
).points

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

Batch search

from qdrant_client.models import QueryRequest

# Multiple queries in one request (search_batch is replaced by query_batch_points)
responses = client.query_batch_points(
    collection_name="documents",
    requests=[
        QueryRequest(query=[0.1, ...], limit=5),
        QueryRequest(query=[0.2, ...], limit=5, filter={"must": [...]}),
        QueryRequest(query=[0.3, ...], limit=10)
    ]
)
# Each element is a QueryResponse; use .points
for resp in responses:
    for point in resp.points:
        print(point.id, point.score)

RAG integration

With sentence-transformers

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()
    response = client.query_points(
        collection_name="knowledge_base",
        query=query_vector,
        limit=top_k
    )
    return [{"text": r.payload["text"], "score": r.score} for r in response.points]

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

With LangChain

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

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)

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 named vector (pass the vector name via `using`)
response = client.query_points(
    collection_name="hybrid_search",
    query=query_dense,
    using="dense",  # Specify which named vector to search
    limit=10
)
results = response.points

Sparse vectors (BM25, SPLADE)

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)

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
response = client.query_points(
    collection_name="quantized",
    query=query,
    search_params={"quantization": {"rescore": True}},  # Rescore top results
    limit=10
)
results = response.points

Payload indexing

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

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

# 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:

# Create payload index for filtered fields
client.create_payload_index(
    collection_name="docs",
    field_name="category",
    field_schema=PayloadSchemaType.KEYWORD
)

Out of memory:

# 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:

# Use timeout and retry
client = QdrantClient(
    host="localhost",
    port=6333,
    timeout=30,
    prefer_grpc=True  # gRPC for better performance
)

When not to use it

Consider alternatives when:

• 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

Limits and gotchas

• The client.search method is removed in qdrant-client 1.14+; use client.query_points instead.
• search_batch is replaced by query_batch_points.
• Always create payload indexes on fields used in filters to avoid slow searches.
• For collections over 1M vectors, enable quantization to reduce memory usage.
• For collections over 10M vectors, consider sharding.
• The on_disk_payload option stores payload on disk, saving RAM at the cost of slower payload access.

What pairs with this

• Advanced Usage - Distributed mode, hybrid search, recommendations
• Troubleshooting - 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: 1.14.0+
• License: Apache 2.0