File size: 1,873 Bytes
59850b8 e7334fb 2e0da1f 0722f22 59850b8 0722f22 59850b8 2e0da1f 59850b8 2e0da1f 59850b8 |
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 |
__import__('pysqlite3')
import sys
sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
import os
import gradio as gr
import chromadb
from sentence_transformers import SentenceTransformer
import pandas as pd
import numpy as np
from chromadb.utils import embedding_functions
from huggingface_hub import InferenceClient
dfs = pd.read_csv('Patents.csv')
ids= [str(x) for x in dfs.index.tolist()]
docs = dfs['text'].tolist()
client = chromadb.Client()
collection = client.get_or_create_collection("patents")
collection.add(documents=docs,ids=ids)
##
def text_embedding(input):
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
return model.encode(input)
def gen_context(query):
vector = text_embedding(query).tolist()
results = collection.query(query_embeddings=vector,n_results=15,include=["documents"])
res = "\n".join(str(item) for item in results['documents'][0])
return res
def chat_completion(query):
length = 1000
context = gen_context(query)
user_prompt = f"""Based on the context:{context}Answer the below query:{query}"""
system_prompt = """You are a helpful AI assistant that can answer questions on the patents dataset. Answer based on the context provided.If you cannot find the correct answer, say I don't know. Be concise and just include the response"""
final_prompt = f"""<s>[INST]<<SYS>>{system_prompt}<</SYS>>{user_prompt}[/INST]"""
return client.text_generation(prompt=final_prompt,max_new_tokens = length).strip()
client = InferenceClient(model = "mistralai/Mixtral-8x7B-Instruct-v0.1")
demo = gr.Interface(fn=chat_completion,
inputs=[gr.Textbox(label="Query", lines=2)],
outputs=[gr.Textbox(label="Result", lines=16)],
title="Chat on Patents Data")
demo.queue().launch(share=True) |