update milvus readme with milvus lite

Signed-off-by: ChengZi <[email protected]>

integrations/milvus-document-store.md

@@ -21,6 +21,7 @@ toc: true
 - [Haystack 2.0](#haystack-20)
  - [Installation](#installation)
  - [Usage](#usage)
+ - [Dive deep usage](#dive-deep-usage)
 - [Haystack 1.x](#haystack-1x)
  - [Installation (1.x)](#installation-1x)
  - [Usage (1.x)](#usage-1x)
@@ -33,60 +34,92 @@ toc: true
 ---
 
 ### Installation
-```console
-pip install -U milvus-haystack
+
+```shell
+pip install --upgrade pymilvus milvus-haystack
 ```
 
 ### Usage
 
-First, to start up a Milvus service, follow the ['Start Milvus'](https://milvus.io/docs/install_standalone-docker.md#Start-Milvus) instructions in the documentation. 
+Use the `MilvusDocumentStore` in a Haystack pipeline as a quick start.
+
+```python
+from haystack import Document
+from milvus_haystack import MilvusDocumentStore
+
+document_store = MilvusDocumentStore(
+ connection_args={"uri": "./milvus.db"}, # Milvus Lite
+ # connection_args={"uri": "http:https://localhost:19530"}, # Milvus standalone docker service.
+ drop_old=True,
+)
+documents = [Document(
+ content="A Foo Document",
+ meta={"page": "100", "chapter": "intro"},
+ embedding=[-10.0] * 128,
+)]
+document_store.write_documents(documents)
+print(document_store.count_documents()) # 1
+```
+In the `connection_args`, setting the URI as a local file, e.g.`./milvus.db`, is the most convenient method, as it automatically utilizes [Milvus Lite](https://milvus.io/docs/milvus_lite.md) to store all data in this file.
+
+If you have large scale of data such as more than a million docs, we recommend setting up a more performant Milvus server on [docker or kubernetes](https://milvus.io/docs/quickstart.md). When using this setup, please use the server URI, e.g.`http:https://localhost:19530`, as your URI.
+
+### Dive deep usage
+
+Prepare an OpenAI API key and set it as an environment variable:
 
-Then, here are the ways to build index, retrieval, and build rag pipeline respectively.
+```shell
+export OPENAI_API_KEY=<your_api_key>
+```
+
+Here are the ways to
+
+- Create the indexing Pipeline
+- Create the retrieval pipeline
+- Create the RAG pipeline
 
-```py
-# Create the indexing Pipeline and index some documents
-import glob
+#### Create the indexing Pipeline and index some documents
+
+```python
 import os
 
 from haystack import Pipeline
 from haystack.components.converters import MarkdownToDocument
-from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
+from haystack.components.embedders import OpenAIDocumentEmbedder, OpenAITextEmbedder
 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("./milvus-document-store.md")
+current_file_path = os.path.abspath(__file__)
+file_paths = [current_file_path] # You can replace it with your own file paths.
 
 document_store = MilvusDocumentStore(
- connection_args={
- "host": "localhost",
- "port": "19530",
- "user": "",
- "password": "",
- "secure": False,
- },
+ connection_args={"uri": "./milvus.db"}, # Milvus Lite
+ # connection_args={"uri": "http:https://localhost:19530"}, # Milvus standalone docker service.
  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("embedder", OpenAIDocumentEmbedder())
 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?"
+#### Create the retrieval pipeline and try a query
+
+```python
+question = "How to set the service uri with milvus lite?" # You can replace it with your own question. 
 
 retrieval_pipeline = Pipeline()
-retrieval_pipeline.add_component("embedder", SentenceTransformersTextEmbedder())
+retrieval_pipeline.add_component("embedder", OpenAITextEmbedder())
 retrieval_pipeline.add_component("retriever", MilvusEmbeddingRetriever(document_store=document_store, top_k=3))
 retrieval_pipeline.connect("embedder", "retriever")
 
@@ -95,11 +128,12 @@ 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
+#### Create the RAG pipeline and try a query
+
+```python
 from haystack.utils import Secret
-from haystack.components.embedders import SentenceTransformersTextEmbedder
 from haystack.components.builders import PromptBuilder
 from haystack.components.generators import OpenAIGenerator
 
@@ -114,7 +148,7 @@ prompt_template = """Answer the following query based on the provided context. I
  """
 
 rag_pipeline = Pipeline()
-rag_pipeline.add_component("text_embedder", SentenceTransformersTextEmbedder())
+rag_pipeline.add_component("text_embedder", OpenAITextEmbedder())
 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")),
@@ -134,7 +168,6 @@ print('RAG answer:', results["generator"]["replies"][0])
 ```
 
 
-
 ## Haystack 1.x