Spaces:
Runtime error
Runtime error
File size: 5,196 Bytes
67d9bfa d3942c3 98d41b7 d3942c3 98d41b7 d3942c3 67d9bfa d3942c3 98d41b7 d3942c3 98d41b7 d3942c3 98d41b7 d3942c3 98d41b7 d3942c3 ccba092 d3942c3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
# app.py 12-04-2024, 19u45m CET
import os
from typing import List
# from langchain.embeddings.openai import OpenAIEmbeddings # ORIGINAL
from langchain_community.embeddings import FastEmbedEmbeddings # JB
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.chains import (
ConversationalRetrievalChain,
)
from langchain.document_loaders import PyPDFLoader
# from langchain.chat_models import ChatOpenAI # ORIGINAL
from langchain_groq import ChatGroq # JB
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.docstore.document import Document
from langchain.memory import ChatMessageHistory, ConversationBufferMemory
from chainlit.types import AskFileResponse
import chainlit as cl
# JB
from dotenv import load_dotenv
import glob
load_dotenv() #
groq_api_key = os.environ['GROQ_API_KEY']
# groq_api_key = "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" # os.environ['GROQ_API_KEY']
print"groq_api_key: ", groq_api_key)
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
system_template = """Use the following pieces of context to answer the users question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
ALWAYS return a "SOURCES" part in your answer.
The "SOURCES" part should be a reference to the source of the document from which you got your answer.
And if the user greets with greetings like Hi, hello, How are you, etc reply accordingly as well.
Example of your response should be:
The answer is foo
SOURCES: xyz
Begin!
----------------
{summaries}"""
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}"),
]
prompt = ChatPromptTemplate.from_messages(messages)
chain_type_kwargs = {"prompt": prompt}
def process_file(file: AskFileResponse):
import tempfile
with tempfile.NamedTemporaryFile(mode="w", delete=False) as tempfile:
with open(tempfile.name, "wb") as f:
f.write(file.content)
pypdf_loader = PyPDFLoader(tempfile.name)
texts = pypdf_loader.load_and_split()
texts = [text.page_content for text in texts]
return texts
@cl.on_chat_start
async def on_chat_start():
files = None
# Wait for the user to upload a file
while files == None:
files = await cl.AskFileMessage(
content="Please upload a PDF file to begin!",
accept=["application/pdf"],
max_size_mb=20,
timeout=180,
).send()
file = files[0]
msg = cl.Message(
content=f"Processing `{file.name}`...", disable_human_feedback=True
)
await msg.send()
# load the file
texts = process_file(file)
print(texts[0])
# Create a metadata for each chunk
metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
# Create a Chroma vector store
# embeddings = OpenAIEmbeddings() # ORIGINAL
embeddings = FastEmbedEmbeddings # JB
docsearch = await cl.make_async(Chroma.from_texts)(
texts, embeddings, metadatas=metadatas
)
message_history = ChatMessageHistory()
memory = ConversationBufferMemory(
memory_key="chat_history",
output_key="answer",
chat_memory=message_history,
return_messages=True,
)
# JB
# llm = ChatGroq(temperature=0.2, groq_api_key=groq_api_key, model_name='mixtral-8x7b-32768')
# Create a chain that uses the Chroma vector store
chain = ConversationalRetrievalChain.from_llm(
# ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True), # ORIGINAL
ChatGroq(temperature=0.2, groq_api_key=groq_api_key, model_name='mixtral-8x7b-32768', streaming=True), # JB
chain_type="stuff",
retriever=docsearch.as_retriever(),
memory=memory,
return_source_documents=True,
)
# Let the user know that the system is ready
msg.content = f"Processing `{file.name}` done. You can now ask questions!"
await msg.update()
cl.user_session.set("chain", chain)
@cl.on_message
async def main(message):
chain = cl.user_session.get("chain") # type: ConversationalRetrievalChain
cb = cl.AsyncLangchainCallbackHandler()
res = await chain.acall(message.content, callbacks=[cb])
answer = res["answer"]
source_documents = res["source_documents"] # type: List[Document]
text_elements = [] # type: List[cl.Text]
if source_documents:
for source_idx, source_doc in enumerate(source_documents):
source_name = f"source_{source_idx}"
# Create the text element referenced in the message
text_elements.append(
cl.Text(content=source_doc.page_content, name=source_name)
)
source_names = [text_el.name for text_el in text_elements]
if source_names:
answer += f"\nSources: {', '.join(source_names)}"
else:
answer += "\nNo sources found"
await cl.Message(content=answer, elements=text_elements).send()
|