引言

前面我們已經(jīng)做好了必要的準(zhǔn)備工作，包括對(duì)相關(guān)知識(shí)點(diǎn)的了解以及環(huán)境的安裝。今天我們將重點(diǎn)關(guān)注代碼方面的內(nèi)容。如果你已經(jīng)具備了Java編程基礎(chǔ)，那么理解Python語法應(yīng)該不會(huì)成為問題，畢竟只是語法的差異而已。隨著時(shí)間的推移，你自然會(huì)逐漸熟悉和掌握這門語言?，F(xiàn)在讓我們開始吧！

環(huán)境安裝命令

在使用之前，我們需要先進(jìn)行一些必要的準(zhǔn)備工作，其中包括執(zhí)行一些命令。如果你已經(jīng)仔細(xì)閱讀了Milvus的官方文檔，你應(yīng)該已經(jīng)了解到了這一點(diǎn)。下面是需要執(zhí)行的一些命令示例：

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(xiàn)在，我們來嘗試使用官方示例，看看在沒有集成LangChain的情況下，我們需要編寫多少代碼才能完成插入、查詢等操作。官方示例已經(jīng)在前面的注釋中詳細(xì)講解了所有的流程?？傮w流程如下：

1. 連接到數(shù)據(jù)庫
2. 創(chuàng)建集合（這里還有分區(qū)的概念，我們不深入討論）
3. 插入向量數(shù)據(jù)（我看官方文檔就簡單插入了一些數(shù)字...）
4. 創(chuàng)建索引（根據(jù)官方文檔的說法，通常在一定數(shù)據(jù)量下是不會(huì)經(jīng)常創(chuàng)建索引的）
5. 查詢數(shù)據(jù)
6. 刪除數(shù)據(jù)
7. 斷開與數(shù)據(jù)庫的連接

通過以上步驟，你會(huì)發(fā)現(xiàn)與連接MySQL數(shù)據(jù)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(jí)版

現(xiàn)在，讓我們來看一下使用LangChain版本的代碼。由于我們使用的是封裝好的Milvus，所以我們需要一個(gè)嵌入模型。在這里，我們選擇了HuggingFaceEmbeddings中的sensenova/piccolo-base-zh模型作為示例，當(dāng)然你也可以選擇其他模型，這里沒有限制。只要能將其作為一個(gè)變量傳遞給LangChain定義的函數(shù)調(diào)用即可。

下面是一個(gè)簡單的示例，包括數(shù)據(jù)庫連接、插入數(shù)據(jù)、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("鏈接數(shù)據(jù)庫")
vector_db = Milvus(
    embeddings,
    connection_args={"host": "localhost", "port": "19530"},
    collection_name="hello_milvus",
) 
print("簡單傳入幾個(gè)值")
vector_db.add_texts(["12345678","789","努力的小雨是一個(gè)知名博主，其名下有公眾號(hào)【靈墨AI探索室】，博客：稀土掘金、博客園、51CTO及騰訊云等","你好啊","我不好"])

print("查詢前3個(gè)最相似的結(jié)果")
docs = vector_db.similarity_search_with_score("你好啊",3)

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

注意，以上代碼只是一個(gè)簡單示例，具體的實(shí)現(xiàn)可能會(huì)根據(jù)你的具體需求進(jìn)行調(diào)整和優(yōu)化。

在langchain版本的代碼中，如果你想要執(zhí)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(wǎng)絡(luò)代理。這里不多贅述，因?yàn)镠uggingFace社區(qū)并不在國內(nèi)。

個(gè)人定制版

接下來，我們將詳細(xì)了解如何調(diào)用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

# 加載env環(huán)境變量里的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(", ")
# 先從數(shù)據(jù)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(jù)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(dāng)你成功運(yùn)行完代碼后，你將會(huì)得到你所期望的答案。如下圖所示，這些答案將會(huì)展示在你的屏幕上。不然，如果系統(tǒng)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(jié)

通過本系列文章的學(xué)習(xí)，我們已經(jīng)對(duì)個(gè)人或企業(yè)知識(shí)庫有了一定的了解。盡管OpenAI已經(jīng)提供了私有知識(shí)庫的部署選項(xiàng)，但是其高昂的成本對(duì)于一些企業(yè)來說可能是難以承受的。無論將來國內(nèi)企業(yè)是否會(huì)提供個(gè)人或企業(yè)知識(shí)庫的解決方案，我們都需要對(duì)其原理有一些了解。無論我們的預(yù)算多少，都可以找到適合自己的玩法，因?yàn)椴煌A(yù)算的玩法也會(huì)有所不同。文章來源地址http://www.zghlxwxcb.cn/news/detail-746340.html

到了這里，關(guān)于????探索人工智能的世界：構(gòu)建智能問答系統(tǒng)之實(shí)戰(zhàn)篇的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！