引言

前面我們已經做好了必要的準備工作，包括對相關知識點的瞭解以及環境的安裝。今天我們將重點關注程式碼方面的內容。如果你已經具備了Java程式設計基礎，那麼理解Python語法應該不會成為問題，畢竟只是語法的差異而已。隨著時間的推移，你自然會逐漸熟悉和掌握這門語言。現在讓我們開始吧！

環境安裝命令

在使用之前，我們需要先進行一些必要的準備工作，其中包括執行一些命令。如果你已經仔細閱讀了Milvus的官方檔案，你應該已經瞭解到了這一點。下面是需要執行的一些命令範例：

pip3 install langchain

pip3 install openai

pip3 install protobuf==3.20.0

pip3 install grpcio-tools

python3 -m pip install pymilvus==2.3.2

python3 -c "from pymilvus import Collection"

快速入門

現在，我們來嘗試使用官方範例，看看在沒有整合LangChain的情況下，我們需要編寫多少程式碼才能完成插入、查詢等操作。官方範例已經在前面的註釋中詳細講解了所有的流程。總體流程如下：

1. 連線到資料庫
2. 建立集合（這裡還有分割區的概念，我們不深入討論）
3. 插入向量資料（我看官方檔案就簡單插入了一些數位...）
4. 建立索引（根據官方檔案的說法，通常在一定資料量下是不會經常建立索引的）
5. 查詢資料
6. 刪除資料
7. 斷開與資料庫的連線

通過以上步驟，你會發現與連線MySQL資料庫的操作非常相似。

# hello_milvus.py demonstrates the basic operations of PyMilvus, a Python SDK of Milvus.
# 1. connect to Milvus
# 2. create collection
# 3. insert data
# 4. create index
# 5. search, query, and hybrid search on entities
# 6. delete entities by PK
# 7. drop collection
import time

import numpy as np
from pymilvus import (
    connections,
    utility,
    FieldSchema, CollectionSchema, DataType,
    Collection,
)

fmt = "\n=== {:30} ===\n"
search_latency_fmt = "search latency = {:.4f}s"
num_entities, dim = 3000, 8

#################################################################################
# 1. connect to Milvus
# Add a new connection alias `default` for Milvus server in `localhost:19530`
# Actually the "default" alias is a buildin in PyMilvus.
# If the address of Milvus is the same as `localhost:19530`, you can omit all
# parameters and call the method as: `connections.connect()`.
#
# Note: the `using` parameter of the following methods is default to "default".
print(fmt.format("start connecting to Milvus"))
connections.connect("default", host="localhost", port="19530")

has = utility.has_collection("hello_milvus")
print(f"Does collection hello_milvus exist in Milvus: {has}")

#################################################################################
# 2. create collection
# We're going to create a collection with 3 fields.
# +-+------------+------------+------------------+------------------------------+
# | | field name | field type | other attributes |       field description      |
# +-+------------+------------+------------------+------------------------------+
# |1|    "pk"    |   VarChar  |  is_primary=True |      "primary field"         |
# | |            |            |   auto_id=False  |                              |
# +-+------------+------------+------------------+------------------------------+
# |2|  "random"  |    Double  |                  |      "a double field"        |
# +-+------------+------------+------------------+------------------------------+
# |3|"embeddings"| FloatVector|     dim=8        |  "float vector with dim 8"   |
# +-+------------+------------+------------------+------------------------------+
fields = [
    FieldSchema(name="pk", dtype=DataType.VARCHAR, is_primary=True, auto_id=False, max_length=100),
    FieldSchema(name="random", dtype=DataType.DOUBLE),
    FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=dim)
]

schema = CollectionSchema(fields, "hello_milvus is the simplest demo to introduce the APIs")

print(fmt.format("Create collection `hello_milvus`"))
hello_milvus = Collection("hello_milvus", schema, consistency_level="Strong")

################################################################################
# 3. insert data
# We are going to insert 3000 rows of data into `hello_milvus`
# Data to be inserted must be organized in fields.
#
# The insert() method returns:
# - either automatically generated primary keys by Milvus if auto_id=True in the schema;
# - or the existing primary key field from the entities if auto_id=False in the schema.

print(fmt.format("Start inserting entities"))
rng = np.random.default_rng(seed=19530)
entities = [
    # provide the pk field because `auto_id` is set to False
    [str(i) for i in range(num_entities)],
    rng.random(num_entities).tolist(),  # field random, only supports list
    rng.random((num_entities, dim)),  # field embeddings, supports numpy.ndarray and list
]

insert_result = hello_milvus.insert(entities)

hello_milvus.flush()
print(f"Number of entities in Milvus: {hello_milvus.num_entities}")  # check the num_entities

################################################################################
# 4. create index
# We are going to create an IVF_FLAT index for hello_milvus collection.
# create_index() can only be applied to `FloatVector` and `BinaryVector` fields.
print(fmt.format("Start Creating index IVF_FLAT"))
index = {
    "index_type": "IVF_FLAT",
    "metric_type": "L2",
    "params": {"nlist": 128},
}

hello_milvus.create_index("embeddings", index)

################################################################################
# 5. search, query, and hybrid search
# After data were inserted into Milvus and indexed, you can perform:
# - search based on vector similarity
# - query based on scalar filtering(boolean, int, etc.)
# - hybrid search based on vector similarity and scalar filtering.
#

# Before conducting a search or a query, you need to load the data in `hello_milvus` into memory.
print(fmt.format("Start loading"))
hello_milvus.load()

# -----------------------------------------------------------------------------
# search based on vector similarity
print(fmt.format("Start searching based on vector similarity"))
vectors_to_search = entities[-1][-2:]
search_params = {
    "metric_type": "L2",
    "params": {"nprobe": 10},
}

start_time = time.time()
result = hello_milvus.search(vectors_to_search, "embeddings", search_params, limit=3, output_fields=["random"])
end_time = time.time()

for hits in result:
    for hit in hits:
        print(f"hit: {hit}, random field: {hit.entity.get('random')}")
print(search_latency_fmt.format(end_time - start_time))

# -----------------------------------------------------------------------------
# query based on scalar filtering(boolean, int, etc.)
print(fmt.format("Start querying with `random > 0.5`"))

start_time = time.time()
result = hello_milvus.query(expr="random > 0.5", output_fields=["random", "embeddings"])
end_time = time.time()

print(f"query result:\n-{result[0]}")
print(search_latency_fmt.format(end_time - start_time))

# -----------------------------------------------------------------------------
# pagination
r1 = hello_milvus.query(expr="random > 0.5", limit=4, output_fields=["random"])
r2 = hello_milvus.query(expr="random > 0.5", offset=1, limit=3, output_fields=["random"])
print(f"query pagination(limit=4):\n\t{r1}")
print(f"query pagination(offset=1, limit=3):\n\t{r2}")

# -----------------------------------------------------------------------------
# hybrid search
print(fmt.format("Start hybrid searching with `random > 0.5`"))

start_time = time.time()
result = hello_milvus.search(vectors_to_search, "embeddings", search_params, limit=3, expr="random > 0.5",
                             output_fields=["random"])
end_time = time.time()

for hits in result:
    for hit in hits:
        print(f"hit: {hit}, random field: {hit.entity.get('random')}")
print(search_latency_fmt.format(end_time - start_time))

###############################################################################
# 6. delete entities by PK
# You can delete entities by their PK values using boolean expressions.
ids = insert_result.primary_keys

expr = f'pk in ["{ids[0]}" , "{ids[1]}"]'
print(fmt.format(f"Start deleting with expr `{expr}`"))

result = hello_milvus.query(expr=expr, output_fields=["random", "embeddings"])
print(f"query before delete by expr=`{expr}` -> result: \n-{result[0]}\n-{result[1]}\n")

hello_milvus.delete(expr)

result = hello_milvus.query(expr=expr, output_fields=["random", "embeddings"])
print(f"query after delete by expr=`{expr}` -> result: {result}\n")

###############################################################################
# 7. drop collection
# Finally, drop the hello_milvus collection
print(fmt.format("Drop collection `hello_milvus`"))
utility.drop_collection("hello_milvus")

升級版

現在，讓我們來看一下使用LangChain版本的程式碼。由於我們使用的是封裝好的Milvus，所以我們需要一個嵌入模型。在這裡，我們選擇了HuggingFaceEmbeddings中的sensenova/piccolo-base-zh模型作為範例，當然你也可以選擇其他模型，這裡沒有限制。只要能將其作為一個變數傳遞給LangChain定義的函數呼叫即可。

下面是一個簡單的範例，包括資料庫連線、插入資料、查詢以及得分情況的定義：

from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Milvus 


model_name = "sensenova/piccolo-base-zh"
embeddings = HuggingFaceEmbeddings(model_name=model_name) 

print("連結資料庫")
vector_db = Milvus(
    embeddings,
    connection_args={"host": "localhost", "port": "19530"},
    collection_name="hello_milvus",
) 
print("簡單傳入幾個值")
vector_db.add_texts(["12345678","789","努力的小雨是一個知名博主，其名下有公眾號【靈墨AI探索室】，部落格：稀土掘金、部落格園、51CTO及騰訊雲等","你好啊","我不好"])

print("查詢前3個最相似的結果")
docs = vector_db.similarity_search_with_score("你好啊",3)

print("檢視其得分情況，分值越低越接近")
for text in docs:
    print('文字:%s,得分:%s'%(text[0].page_content,text[1]))

注意，以上程式碼只是一個簡單範例，具體的實現可能會根據你的具體需求進行調整和優化。

在langchain版本的程式碼中，如果你想要執行除了自己需要開啟docker中的milvus容器之外的操作，還需要確保你擁有網路代理。這裡不多贅述，因為HuggingFace社群並不在國內。

個人客製化版

接下來，我們將詳細瞭解如何呼叫openai模型來回答問題！

from dotenv import load_dotenv
from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate; 
from langchain import PromptTemplate
from langchain.chains import LLMChain 
from langchain.chat_models.openai import ChatOpenAI 
from langchain.schema import BaseOutputParser

# 載入env環境變數裡的key值
load_dotenv()
# 格式化輸出
class CommaSeparatedListOutputParser(BaseOutputParser):
    """Parse the output of an LLM call to a comma-separated list."""

    def parse(self, text: str):
        """Parse the output of an LLM call."""
        return text.strip().split(", ")
# 先從資料庫查詢問題解
docs = vector_db.similarity_search("努力的小雨是誰？")
doc = docs[0].page_content

chat = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0)
template = "請根據我提供的資料回答問題，資料： {input_docs}"
system_message_prompt = SystemMessagePromptTemplate.from_template(template)
human_template = "{text}"
human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)

chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])

# chat_prompt.format_messages(input_docs=doc, text="努力的小雨是誰？")
chain = LLMChain(
    llm=chat,
    prompt=chat_prompt,
    output_parser=CommaSeparatedListOutputParser()
)
chain.run(input_docs=doc, text="努力的小雨是誰？") 

當你成功執行完程式碼後，你將會得到你所期望的答案。如下圖所示，這些答案將會展示在你的螢幕上。不然，如果系統不知道這些問題的答案，那它又如何能夠給出正確的回答呢？

總結

通過本系列文章的學習，我們已經對個人或企業知識庫有了一定的瞭解。儘管OpenAI已經提供了私有知識庫的部署選項，但是其高昂的成本對於一些企業來說可能是難以承受的。無論將來國內企業是否會提供個人或企業知識庫的解決方案，我們都需要對其原理有一些瞭解。無論我們的預算多少，都可以找到適合自己的玩法，因為不同預算的玩法也會有所不同。