milvus-haystack 0.0.5

No project description provided

Milvus Document Store for Haystack

Installation

pip install milvus-haystack

Usage

First, to start up a Milvus service, follow the 'Start Milvus' instructions in the documentation.

Then, to use the MilvusDocumentStore in a Haystack pipeline"

from haystack import Document
from milvus_haystack import MilvusDocumentStore

document_store = MilvusDocumentStore()
documents = [Document(
    content="A Foo Document",
    meta={"page": "100", "chapter": "intro"},
    embedding=[-10.0] * 128,
)]
document_store.write_documents(documents)
document_store.count_documents()  # 1

Dive deep usage

Here are the ways to build index, retrieval, and build rag pipeline respectively.

Create the indexing Pipeline and index some documents

import glob
import os

from haystack import Pipeline
from haystack.components.converters import MarkdownToDocument
from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
from haystack.components.preprocessors import DocumentSplitter
from haystack.components.writers import DocumentWriter

from milvus_haystack import MilvusDocumentStore
from milvus_haystack.milvus_embedding_retriever import MilvusEmbeddingRetriever

file_paths = glob.glob("./your_docs.md")

document_store = MilvusDocumentStore(
    connection_args={
        "host": "localhost",
        "port": "19530",
        "user": "",
        "password": "",
        "secure": False,
    },
    drop_old=True,
)
indexing_pipeline = Pipeline()
indexing_pipeline.add_component("converter", MarkdownToDocument())
indexing_pipeline.add_component("splitter", DocumentSplitter(split_by="sentence", split_length=2))
indexing_pipeline.add_component("embedder", SentenceTransformersDocumentEmbedder())
indexing_pipeline.add_component("writer", DocumentWriter(document_store))
indexing_pipeline.connect("converter", "splitter")
indexing_pipeline.connect("splitter", "embedder")
indexing_pipeline.connect("embedder", "writer")
indexing_pipeline.run({"converter": {"sources": file_paths}})

print("Number of documents:", document_store.count_documents())

Create the retrieval pipeline and try a query

question = "What is Milvus?"

retrieval_pipeline = Pipeline()
retrieval_pipeline.add_component("embedder", SentenceTransformersTextEmbedder())
retrieval_pipeline.add_component("retriever", MilvusEmbeddingRetriever(document_store=document_store, top_k=3))
retrieval_pipeline.connect("embedder", "retriever")

retrieval_results = retrieval_pipeline.run({"embedder": {"text": question}})

for doc in retrieval_results["retriever"]["documents"]:
    print(doc.content)
    print("-" * 10)

Create the RAG pipeline and try a query

from haystack.utils import Secret
from haystack.components.embedders import SentenceTransformersTextEmbedder
from haystack.components.builders import PromptBuilder
from haystack.components.generators import OpenAIGenerator

prompt_template = """Answer the following query based on the provided context. If the context does
                     not include an answer, reply with 'I don't know'.\n
                     Query: {{query}}
                     Documents:
                     {% for doc in documents %}
                        {{ doc.content }}
                     {% endfor %}
                     Answer: 
                  """

rag_pipeline = Pipeline()
rag_pipeline.add_component("text_embedder", SentenceTransformersTextEmbedder())
rag_pipeline.add_component("retriever", MilvusEmbeddingRetriever(document_store=document_store, top_k=3))
rag_pipeline.add_component("prompt_builder", PromptBuilder(template=prompt_template))
rag_pipeline.add_component("generator", OpenAIGenerator(api_key=Secret.from_token(os.getenv("OPENAI_API_KEY")),
                                                        generation_kwargs={"temperature": 0}))
rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
rag_pipeline.connect("retriever.documents", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "generator")

results = rag_pipeline.run(
    {
        "text_embedder": {"text": question},
        "prompt_builder": {"query": question},
    }
)
print('RAG answer:', results["generator"]["replies"][0])

License

milvus-haystack is distributed under the terms of the Apache-2.0 license.