From 1ced93ca1ab7eac89feda2da0183e30f24cd5c53 Mon Sep 17 00:00:00 2001
From: ChengZi <chen.zhang@zilliz.com>
Date: Thu, 14 Mar 2024 16:56:09 +0800
Subject: [PATCH] refine doc

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
---
 README.md | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 98 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index dbc68a0..fbe7c9e 100644
--- a/README.md
+++ b/README.md
@@ -1,10 +1,13 @@
 # Milvus Document Store for Haystack
 
+[![PyPI - Version](https://img.shields.io/pypi/v/milvus-haystack.svg)](https://pypi.org/project/milvus-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/milvus-haystack.svg)](https://pypi.org/project/milvus-haystack)
+
 
 ## Installation
 
 ```console
-pip install -e milvus-haystack
+pip install milvus-haystack
 ```
 
 ## Usage
@@ -26,6 +29,100 @@ 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.
+
+```py
+# 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](https://spdx.org/licenses/Apache-2.0.html) license.
\ No newline at end of file