Spaces:
Runtime error
Runtime error
File size: 3,837 Bytes
694d535 |
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 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
import streamlit as st
from PyPDF2 import PdfReader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.agents import initialize_agent, AgentType
from langchain.callbacks import StreamlitCallbackHandler
from langchain.chat_models import ChatOpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
import os
from dotenv import load_dotenv
load_dotenv()
# provide the path of pdf file/files.
pdfreader = PdfReader('input_data/nvidia_10k.pdf')
with st.sidebar:
openai_api_key = st.text_input("OpenAI API Key", type="password")
"[Get an OpenAI API key](https://platform.openai.com/account/api-keys)"
@st.cache_data
def split_chunk_text(input_path="input_data/nvidia_10k.pdf"):
from typing_extensions import Concatenate
# read text from pdf
pdfreader = PdfReader(input_path)
raw_text = ''
for i, page in enumerate(pdfreader.pages):
content = page.extract_text()
if content:
raw_text += content
text_splitter = CharacterTextSplitter(
separator = "\n",
chunk_size = 800,
chunk_overlap = 200,
length_function = len,
)
texts = text_splitter.split_text(raw_text)
return texts
with st.form("my_form"):
texts = split_chunk_text()
embeddings = OpenAIEmbeddings(
model="text-embedding-3-small"
)
vector_store = FAISS.from_texts(texts, embeddings)
retriever = vector_store.as_retriever()
text = st.text_area("Enter question:", " ")
submitted = st.form_submit_button("Submit")
if not openai_api_key:
st.info("Please add your OpenAI API key to continue.")
elif submitted:
#texts = split_chunk_text()
from operator import itemgetter
from langchain.prompts import ChatPromptTemplate
template = """Answer the question based only on the following context. If you cannot answer the question with the context, please respond with 'I don't know':
Context:
{context}
Question:
{question}
"""
prompt = ChatPromptTemplate.from_template(template)
primary_qa_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
retrieval_augmented_qa_chain = (
# INVOKE CHAIN WITH: {"question" : "<<SOME USER QUESTION>>"}
# "question" : populated by getting the value of the "question" key
# "context" : populated by getting the value of the "question" key and chaining it into the base_retriever
{"context": itemgetter("question") | retriever, "question": itemgetter("question")}
# "context" : is assigned to a RunnablePassthrough object (will not be called or considered in the next step)
# by getting the value of the "context" key from the previous step
| RunnablePassthrough.assign(context=itemgetter("context"))
# "response" : the "context" and "question" values are used to format our prompt object and then piped
# into the LLM and stored in a key called "response"
# "context" : populated by getting the value of the "context" key from the previous step
| {"response": prompt | primary_qa_llm, "context": itemgetter("context")}
)
#query = "Who is liable in case of an accident if a learner is driving with an instructor?"
result = retrieval_augmented_qa_chain.invoke({"question" : text})
st.info(result["response"].content) |