-
Notifications
You must be signed in to change notification settings - Fork 0
/
continuous.py
95 lines (77 loc) · 3.17 KB
/
continuous.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
# setup environment variables
from dotenv import load_dotenv
import os
load_dotenv()
openai_api_key = os.getenv("OPENAI_API_KEY")
# import LangChain packages
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.document_loaders import WebBaseLoader
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_retrieval_chain
from langchain.chains import create_history_aware_retriever
from langchain_core.prompts import MessagesPlaceholder
from langchain_core.messages import HumanMessage, AIMessage
import textwrap
def consoleformat(input,width=100):
formatted=textwrap.fill(input,width)
return formatted
llm = ChatOpenAI()
# Takes question and retrieved documents and generates an answer
prompt = ChatPromptTemplate.from_template("""Answer the following question based only on the provided context:
<context>
{context}
</context>
Question: {input}""")
document_chain = create_stuff_documents_chain(llm, prompt)
# Convert output to string format
output_parser = StrOutputParser()
# Chain everything together
chain = prompt | llm | output_parser
# Load reference data to index
loader = WebBaseLoader("/Users/jacintogomez/Downloads/KOearnings.pdf")
docs = loader.load()
# Embedding model
embeddings = OpenAIEmbeddings()
# Index data into a vectorstore
text_splitter = RecursiveCharacterTextSplitter()
documents = text_splitter.split_documents(docs)
vector = FAISS.from_documents(documents, embeddings)
# Use retriever to dynamically select relevant documents
retriever = vector.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
prompt = ChatPromptTemplate.from_messages([
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}"),
("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
])
retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")]
retriever_chain.invoke({
"chat_history": chat_history,
"input": "Tell me how"
})
prompt = ChatPromptTemplate.from_messages([
("system", "Answer the user's questions based on the below context:\n\n{context}"),
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}"),
])
document_chain = create_stuff_documents_chain(llm, prompt)
retrieval_chain = create_retrieval_chain(retriever_chain, document_chain)
# chat_history = [HumanMessage(content="Is Satoshi Nakamoto the inventor of Bitcoin?"), AIMessage(content="Yes!")]
# answer=retrieval_chain.invoke({
# "chat_history": chat_history,
# "input": "Tell me who he is"
# })
while True:
user_msg=input("Q: ")
chat_history=[]
answer=retrieval_chain.invoke({
"chat_history":chat_history,
"input":user_msg
})
print(consoleformat(answer['answer']))