Vector Retrieval Service for Milvus:Full-text and hybrid search with BM25 for RAG

Step 1: Install dependency libraries

pip3 install pymilvus langchain dashscope

Step 2: Prepare data

This example chunks the official Milvus documentation with LangChain, generates embeddings using the text-embedding-v2 model, and inserts the results into Milvus.

from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import DashScopeEmbeddings
from pymilvus import MilvusClient, DataType, Function, FunctionType

dashscope_api_key = "<YOUR_DASHSCOPE_API_KEY>"
milvus_url = "<YOUR_MMILVUS_URL>"
user_name = "root"
password = "<YOUR_PASSWORD>"
collection_name = "milvus_overview"
dense_dim = 1536

loader = WebBaseLoader([
    'https://raw.githubusercontent.com/milvus-io/milvus-docs/refs/heads/v2.5.x/site/en/about/overview.md'
])

docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=256)

# Use LangChain to chunk the input document by chunk_size
all_splits = text_splitter.split_documents(docs)

embeddings = DashScopeEmbeddings(
    model="text-embedding-v2", dashscope_api_key=dashscope_api_key
)

text_contents = [doc.page_content for doc in all_splits]

vectors = embeddings.embed_documents(text_contents)


client = MilvusClient(
    uri=f"http://{milvus_url}:19530",
    token=f"{user_name}:{password}",
)

schema = MilvusClient.create_schema(
    enable_dynamic_field=True,
)

analyzer_params = {
    "type": "english"
}

# Add fields to schema
schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True, auto_id=True)
schema.add_field(field_name="text", datatype=DataType.VARCHAR, max_length=65535, enable_analyzer=True, analyzer_params=analyzer_params, enable_match=True)
schema.add_field(field_name="sparse_bm25", datatype=DataType.SPARSE_FLOAT_VECTOR)
schema.add_field(field_name="dense", datatype=DataType.FLOAT_VECTOR, dim=dense_dim)

bm25_function = Function(
   name="bm25",
   function_type=FunctionType.BM25,
   input_field_names=["text"],
   output_field_names="sparse_bm25",
)
schema.add_function(bm25_function)

index_params = client.prepare_index_params()

# Add indexes
index_params.add_index(
    field_name="dense",
    index_name="dense_index",
    index_type="IVF_FLAT",
    metric_type="IP",
    params={"nlist": 128},
)

index_params.add_index(
    field_name="sparse_bm25",
    index_name="sparse_bm25_index",
    index_type="SPARSE_WAND",
    metric_type="BM25"
)

# Create collection
client.create_collection(
    collection_name=collection_name,
    schema=schema,
    index_params=index_params
)

data = [
    {"dense": vectors[idx], "text": doc}
    for idx, doc in enumerate(text_contents)
]

# Insert data
res = client.insert(
    collection_name=collection_name,
    data=data
)

print(f"Generated {len(vectors)} vectors, dimension: {len(vectors[0])}")

Replace the following parameters with your actual values.

The bm25_function object tells Milvus to automatically convert the text column into sparse vectors.

For Chinese documents, specify a chinese analyzer instead.

# Define tokenizer parameters
analyzer_params = {
    "type": "chinese"  # Specify the tokenizer type as chinese
}

# Add a text field to the schema and enable the tokenizer
schema.add_field(
    field_name="text",                      # Field name
    datatype=DataType.VARCHAR,              # Data type: string (VARCHAR)
    max_length=65535,                       # Maximum length: 65535 characters
    enable_analyzer=True,                   # Enable the tokenizer
    analyzer_params=analyzer_params         # Tokenizer parameters
)

Step 3: Perform full-text search

The following example performs a full-text search using the BM25 sparse vector field.

from pymilvus import MilvusClient

# Create a Milvus client.
client = MilvusClient(
    uri="http://c-xxxx.milvus.aliyuncs.com:19530",  # The public network address of the Milvus instance.
    token="<yourUsername>:<yourPassword>",  # The username and password to log on to the Milvus instance.
    db_name="default"  # The name of the database to connect to. This example uses the default database.
)

search_params = {
    'params': {'drop_ratio_search': 0.2},
}

full_text_search_res = client.search(
    collection_name='milvus_overview',
    data=['what makes milvus so fast?'],
    anns_field='sparse_bm25',
    limit=3,
    search_params=search_params,
    output_fields=["text"],
)

for hits in full_text_search_res:
    for hit in hits:
        print(hit)
        print("\n")

"""
{'id': 456165042536597485, 'distance': 6.128782272338867, 'entity': {'text': '## What Makes Milvus so Fast？\n\nMilvus was designed from day one to be a highly efficient vector database system. In most cases, Milvus outperforms other vector databases by 2-5x (see the VectorDBBench results). This high performance is the result of several key design decisions:\n\n**Hardware-aware Optimization**: To accommodate Milvus in various hardware environments, we have optimized its performance specifically for many hardware architectures and platforms, including AVX512, SIMD, GPUs, and NVMe SSD.\n\n**Advanced Search Algorithms**: Milvus supports a wide range of in-memory and on-disk indexing/search algorithms, including IVF, HNSW, DiskANN, and more, all of which have been deeply optimized. Compared to popular implementations like FAISS and HNSWLib, Milvus delivers 30%-70% better performance.'}}

{'id': 456165042536597487, 'distance': 4.760214805603027, 'entity': {'text': "## What Makes Milvus so Scalable\n\nIn 2022, Milvus supported billion-scale vectors, and in 2023, it scaled up to tens of billions with consistent stability, powering large-scale scenarios for over 300 major enterprises, including Salesforce, PayPal, Shopee, Airbnb, eBay, NVIDIA, IBM, AT&T, LINE, ROBLOX, Inflection, etc.\n\nMilvus's cloud-native and highly decoupled system architecture ensures that the system can continuously expand as data grows:\n\n![Highly decoupled system architecture of Milvus](../../../assets/highly-decoupled-architecture.png)"}}
"""

Step 4: Keyword match

Keyword matching narrows the search scope by filtering on exact terms before vector search. Set enable_analyzer and enable_match to True in the schema definition.

filter = "TEXT_MATCH(text, 'query') and TEXT_MATCH(text, 'node')"

text_match_res = client.search(
    collection_name="milvus_overview",
    anns_field="dense",
    data=query_embeddings,
    filter=filter,
    search_params={"params": {"nprobe": 10}},
    limit=2,
    output_fields=["text"]
)

filter = "TEXT_MATCH(text, 'scalable fast')"

text_match_res = client.query(
    collection_name="milvus_overview",
    filter=filter,
    output_fields=["text"]
)

Step 5: Hybrid search and RAG

Combine dense vector search and BM25 full-text search, then merge results with Reciprocal Rank Fusion (RRF) to improve recall and precision.

Example:

from pymilvus import MilvusClient
from pymilvus import AnnSearchRequest, RRFRanker
from langchain_community.embeddings import DashScopeEmbeddings
from dashscope import Generation

# Create a Milvus client.
client = MilvusClient(
    uri="http://c-xxxx.milvus.aliyuncs.com:19530",  # The public network address of the Milvus instance.
    token="<yourUsername>:<yourPassword>",  # The username and password to log on to the Milvus instance.
    db_name="default"  # The name of the database to connect to. This example uses the default database.
)

collection_name = "milvus_overview"

# Replace with your DashScope API key
dashscope_api_key = "<YOUR_DASHSCOPE_API_KEY>"

# Initialize the embedding model
embeddings = DashScopeEmbeddings(
    model="text-embedding-v2",  # Use the text-embedding-v2 model.
    dashscope_api_key=dashscope_api_key
)

# Define the query
query = "Why does Milvus run so scalable?"

# Embed the query and generate the corresponding vector representation
query_embeddings = embeddings.embed_documents([query])

# Set the top K result count
top_k = 5  # Get the top 5 docs related to the query

# Define the parameters for the dense vector search
search_params_dense = {
    "metric_type": "IP",
    "params": {"nprobe": 2}
}

# Create a dense vector search request
request_dense = AnnSearchRequest([query_embeddings[0]], "dense", search_params_dense, limit=top_k)

# Define the parameters for the BM25 text search
search_params_bm25 = {
    "metric_type": "BM25"
}

# Create a BM25 text search request
request_bm25 = AnnSearchRequest([query], "sparse_bm25", search_params_bm25, limit=top_k)

# Combine the two requests
reqs = [request_dense, request_bm25]

# Initialize the RRF ranking algorithm
ranker = RRFRanker(100)

# Perform the hybrid search
hybrid_search_res = client.hybrid_search(
    collection_name=collection_name,
    reqs=reqs,
    ranker=ranker,
    limit=top_k,
    output_fields=["text"]
)

# Extract the context from hybrid search results
context = []
print("Top K Results:")
for hits in hybrid_search_res:  # Use the correct variable here
    for hit in hits:
        context.append(hit['entity']['text'])  # Extract text content to the context list
        print(hit['entity']['text'])  # Output each retrieved document


# Define a function to get an answer based on the query and context
def getAnswer(query, context):
    prompt = f'''Please answer my question based on the content within:
    ```
    {context}
    ```
    My question is: {query}.
    '''
    # Call the generation module to get an answer
    rsp = Generation.call(model='qwen-turbo', prompt=prompt)
    return rsp.output.text

# Get the answer
answer = getAnswer(query, context)

print(answer)


# Expected output excerpt
"""
Milvus is highly scalable due to its cloud-native and highly decoupled system architecture. This architecture allows the system to continuously expand as data grows. Additionally, Milvus supports three deployment modes that cover a wide...
"""