Spaces:
Sleeping
Sleeping
File size: 2,746 Bytes
72c1b8c |
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 |
from sentence_transformers import SentenceTransformer
from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.llms import HuggingFaceHub
import openai
import streamlit as st
import re
#openai_api_key = "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"
model = SentenceTransformer('sentence-transformers/multi-qa-MiniLM-L6-cos-v1')
# Define the embedding function using HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(model_name = 'sentence-transformers/multi-qa-MiniLM-L6-cos-v1')
vectordb = Chroma(persist_directory= r"\vector db", #enter chroma directory
embedding_function=embeddings)
#index = pinecone.Index('langchain-chatbot')
# Create a retriever from the Chroma object
retriever = vectordb.as_retriever()
def find_match(input_text):
# Retrieve relevant documents based on the input query
docs = retriever.get_relevant_documents(input_text)
match_texts = [doc.page_content for doc in docs]
# Return the concatenated texts of the relevant documents
return "\n".join(match_texts)
from transformers import pipeline
# Load the text generation pipeline from Hugging Face
text_generator = pipeline("text-generation", model="gpt2")
def query_refiner(conversation, query):
# Formulate the prompt for the model
prompt = f"Given the following user query and conversation log, formulate a question that would be the most relevant to provide the user with an answer from a knowledge base.\n\nCONVERSATION LOG: \n{conversation}\n\nQuery: {query}\n\nRefined Query:"
# Generate the response using the Hugging Face model
response = text_generator(prompt, max_length=256, temperature=0.7, top_p=1.0, pad_token_id=text_generator.tokenizer.eos_token_id)
# Extract the refined query from the response
refined_query = response[0]['generated_text'].split('Refined Query:')[-1].strip()
return refined_query
def get_conversation_string():
conversation_string = ""
for i in range(len(st.session_state['responses'])-1):
conversation_string += "Human: "+st.session_state['requests'][i] + "\n"
conversation_string += "Bot: "+ st.session_state['responses'][i+1] + "\n"
return conversation_string
"""
from openai import OpenAI
from audio_recorder_streamlit import audio_recorder
client=OpenAI(api_key="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")
def speech_to_text(audio_data):
with open(audio_data, "rb") as audio_file:
transcript = client.audio.transcriptions.create(
model="whisper-1",
response_format="text",
file=audio_file
)
return transcript
"""
|