一文搞懂LangChain
什么是 LangChain？
谷歌的 BERT OpenAI 的 GPT-3 谷歌 LaMDA 谷歌 PaLM Meta AI 的 LLaMA OpenAI 的 GPT-4 ……
# Importing modules
from langchain.llms import OpenAI
#Here we are using text-ada-001 but you can change it
llm = OpenAI(model_name="text-ada-001", n=2, best_of=2)
#Ask anything
llm("Tell me a joke")
'\n\nWhy did the chicken cross the road?\n\nTo get to the other side.'
llm_result = llm.generate(["Tell me a poem"]*15)
[Generation(text="\n\nWhat if love neverspeech\n\nWhat if love never ended\n\nWhat if love was only a feeling\n\nI'll never know this love\n\nIt's not a feeling\n\nBut it's what we have for each other\n\nWe just know that love is something strong\n\nAnd we can't help but be happy\n\nWe just feel what love is for us\n\nAnd we love each other with all our heart\n\nWe just don't know how\n\nHow it will go\n\nBut we know that love is something strong\n\nAnd we'll always have each other\n\nIn our lives."),
Generation(text='\n\nOnce upon a time\n\nThere was a love so pure and true\n\nIt lasted for centuries\n\nAnd never became stale or dry\n\nIt was moving and alive\n\nAnd the heart of the love-ick\n\nIs still beating strong and true.')]
from langchain import PromptTemplate
# This template will act as a blue print for prompt
template = """
I want you to act as a naming consultant for new companies.
What is a good name for a company that makes {product}?
"""
prompt = PromptTemplate(
input_variables=["product"],
template=template,
)
prompt.format(product="colorful socks")
# -> I want you to act as a naming consultant for new companies.
# -> What is a good name for a company that makes colorful socks?
from langchain.memory import ChatMessageHistory
history = ChatMessageHistory()
history.add_user_message("hi!")
history.add_ai_message("whats up?")
history.messages
[HumanMessage(content='hi!', additional_kwargs={}),
AIMessage(content='whats up?', additional_kwargs={})]
#Here we are chaining everything
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
)
human_message_prompt = HumanMessagePromptTemplate(
prompt=PromptTemplate(
template="What is a good name for a company that makes {product}?",
input_variables=["product"],
)
)
chat_prompt_template = ChatPromptTemplate.from_messages([human_message_prompt])
chat = ChatOpenAI(temperature=0.9)
# Temperature is about randomness in answer more the temp, random the answer
#Final Chain
chain = LLMChain(llm=chat, prompt=chat_prompt_template)
print(chain.run("colorful socks"))
接收用户输入。 代理根据输入决定是否使用某个工具，以及该工具的输入应该是什么。 调用该工具，并记录观测结果（即使用该工具和输入调用后得到的输出）。 将工具、工具输入和观测结果的历史传递回代理，代理决定下一步应该采取的步骤。 重复上述步骤，直到代理决定不再需要使用工具，然后直接向用户作出回应。
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
tools = load_tools(["serpapi", "llm-math"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
LangChain 的实际应用
# IMPORTS
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains import ConversationalRetrievalChain
from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
from PyPDF2 import PdfReader
from langchain import OpenAI, VectorDBQA
from langchain.vectorstores import Chroma
from langchain.prompts import PromptTemplate
from langchain.chains import ConversationChain
from langchain.document_loaders import TextLoader
# from langchain import ConversationalRetrievalChain
from langchain.chains.question_answering import load_qa_chain
from langchain import LLMChain
# from langchain import retrievers
import langchain
from langchain.chains.conversation.memory import ConversationBufferMemory
前往 OpenAI API 页面， 点击 “Create new secret key（创建新的密钥） ” 那将是你的 API 密钥。请将其粘贴在下方
import os
os.environ["OPENAI_API_KEY"] = "sk-YOUR API KEY"
llm = ChatOpenAI(temperature=0,model_name="gpt-3.5-turbo")
# Custom data
from langchain.document_loaders import DirectoryLoader
pdf_loader = PdfReader(r'Your PDF location')
# excel_loader = DirectoryLoader('./Reports/', glob="**/*.txt")
# word_loader = DirectoryLoader('./Reports/', glob="**/*.docx")
#Preprocessing of file
raw_text = ''
for i, page in enumerate(pdf_loader.pages):
text = page.extract_text()
if text:
raw_text += text
# print(raw_text[:100])
text_splitter = CharacterTextSplitter(
separator = "\n",
chunk_size = 1000,
chunk_overlap = 200,
length_function = len,
)
texts = text_splitter.split_text(raw_text)
embeddings = OpenAIEmbeddings()
# vectorstore = Chroma.from_documents(documents, embeddings)
vectorstore = FAISS.from_texts(texts, embeddings)
prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say GTGTGTGTGTGTGTGTGTG, don't try to make up an answer.
{context}
Question: {question}
Helpful Answer:"""
QA_PROMPT = PromptTemplate(
template=prompt_template, input_variables=['context',"question"]
)
qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0.8), vectorstore.as_retriever(),qa_prompt=QA_PROMPT)
# Front end web app
import gradio as gr
with gr.Blocks() as demo:
gr.Markdown("## Grounding DINO ChatBot")
chatbot = gr.Chatbot()
msg = gr.Textbox()
clear = gr.Button("Clear")
chat_history = []
def user(user_message, history)
print("Type of use msg:",type(user_message))
# Get response from QA chain
response = qa({"question": user_message, "chat_history": history})
# Append user message and response to chat history
history.append((user_message, response["answer"]))
print(history)
return gr.update(value=""), history
msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False)
clear.click(lambda: None, None, chatbot, queue=False)
############################################
if __name__ == "__main__":
demo.launch(debug=True)
LangChain 的 Token 和模型
import tiktoken
#Write function to take string input and return number of tokens
def num_tokens_from_string(string: str, encoding_name: str) -> int:
"""Returns the number of tokens in a text string."""
encoding = tiktoken.encoding_for_model(encoding_name)
num_tokens = len(encoding.encode(string))
return num_tokens
prompt = []
for i in data:
prompt.append((num_tokens_from_string(i['prompt'], "davinci")))
completion = []
for j in data:
completion.append((num_tokens_from_string(j['completion'], "davinci")))
res_list = []
for i in range(0, len(prompt)):
res_list.append(prompt[i] + completion[i])
no_of_final_token = 0
for i in res_list:
no_of_final_token+=i
print("Number of final token",no_of_final_token)
Number of final token 2094
GPT-3 GPT-3.5 GPT-4
总结
作者：Chinmay Bhalerao 来源：分布式实验室 原文：https://pub.towardsai.net/tokens-and-models-understanding-langchain-%EF%B8%8F-part-3-e471aececf19
本文为 @ 寂静日光 创作并授权 21CTO 发布，未经许可，请勿转载。
内容授权事宜请您联系 webmaster@21cto.com或关注 21CTO 公众号。
该文观点仅代表作者本人，21CTO 平台仅提供信息存储空间服务。
评论
