Spaces:
Runtime error
Runtime error
File size: 2,753 Bytes
eaf119d |
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 |
from pymilvus import utility, DataType, FieldSchema, CollectionSchema, Collection
from utils import connect_vector_db, load_collection, convert_query, clean_query
from routing import routing_query
from search import search_chunks
from sentence_transformers import SentenceTransformer
import re
import gradio as gr
import requests
import json
def search(query, path_stop_words, path_define, model_name, topk):
collection_name = routing_query(query, path_stop_words, path_define)
results = search_chunks(query, model_name, collection_name, topk)
refs, relevant_chunks = [], []
pattern = r"'chunk_ref': '([^']*)', 'chunk_text': '([^']*)'"
for sample in results:
matches = re.findall(pattern, str(sample))
for match in matches:
refs.append(match[0])
relevant_chunks.append(match[1])
return refs, relevant_chunks
def response_saola2m(PROMPT, temperature=0.7):
url = "https://api.fpt.ai/nlp/llm/api/v1/completions"
headers = {
'Authorization': 'Bearer sk-8oIY6XLrokZEJMl6aopCuQ',
'Content-Type': 'application/json',
}
data = {
"model": "SaoLa2M-instruct",
"prompt": PROMPT,
"temperature": temperature,
"max_tokens": 512
}
response = requests.post(url, headers=headers, json=data)
response_text = response.text
response_json = json.loads(response_text)
result = response_json['choices'][0]['text']
return result
PATH_STOP_WORDS = 'vi_stopword.txt'
PATH_DEFINE = 'define.json'
MODEL_NAME = 'qminh369/datn-dense_embedding'
TOPK = 5
connect_vector_db()
def answer(question):
refs, relevant_chunks = search(question, PATH_STOP_WORDS, PATH_DEFINE, MODEL_NAME, TOPK)
INSTRUCTION = "Hãy trả lời câu hỏi sau dựa trên thông tin được cung cấp. Nếu thông tin được cung cấp không liên quan dến câu hỏi thì trả về câu trả lời 'Không có thông tin'"
INPUT_TEXT = "\n".join(relevant_chunks)
PROMPT = f"<s>[INST] Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{INSTRUCTION}\n\n{question}\n\n### Input:\n{INPUT_TEXT}\n\n[/INST]### Response:\n"
print(PROMPT)
response = response_saola2m(PROMPT, temperature=0)
ref = "\n" + "Trích dẫn từ: " + refs[0]
response = response + ref
return response.strip()
def chatbot(question, history=[]):
output = answer(question)
history.append((question, output))
return history, history
demo = gr.Interface(
fn=chatbot,
inputs=["text", "state"],
outputs=["chatbot", "state"])
demo.queue().launch(share=True)
|