Duplicate from xl2533/WhatToAsk

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: WhatToAsk
+emoji: ⚡
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+duplicated_from: xl2533/WhatToAsk
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,30 @@
+# -*-coding:utf-8 -*-
+
+import os
+import gradio as gr
+from qa import *
+
+with gr.Blocks(title="QA Generation", theme=gr.themes.Glass()) as demo:
+    openai_key = gr.Textbox(type='password', label='输入 API key')
+    gr.Markdown("## Question Answer Generation")
+    with gr.Row():
+        input = gr.Textbox(label='上下文')
+        qa = gr.JSON(label='问题&回答对')
+    gen = gr.Button(value='generate')
+
+    gr.Markdown('## Answer Generation')
+    with gr.Row():
+        context = gr.Textbox(label='上下文')
+        question = gr.Textbox(label ='问题')
+        answer = gr.Textbox(label='答案')
+    ask = gr.Button(value='ask')
+
+
+    ## Callback
+    gen.click(get_qa, [input, openai_key], [qa])
+
+    ask.click(get_answer, [context, question, openai_key], [answer])
+
+
+    # launch
+    demo.queue().launch(debug=True)

prompt.py

@@ -0,0 +1,17 @@
+# -*-coding:utf-8 -*-
+
+QA_gen_user_prompt = """你是金融领域负责出题的老师。给一段文本，你需要想出合适的问题/答案对，包括但不限于经济，政策，金融市场，公司理财，基金等相关领域。返回如下json格式
+{{"问题":$问题,"回答":$回答}}
+文本: {text}
+问题/回答对:
+"""
+
+QA_gen_sys_prompt = ""
+
+QA_answer_sys_prompt = ""
+
+QA_answer_user_prompt = """你是一个金融问答系统，只使用已有上下文进行问题回答，当上下文无法回答对应问题时，直接回复'无法回答'。
+上下文:{text}
+问题:{question}
+回答: 
+"""

qa.py

@@ -0,0 +1,40 @@
+# -*-coding:utf-8 -*-
+import json
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from langchain.chains import LLMChain
+from prompt import *
+from langchain.chat_models import ChatOpenAI
+
+
+def get_qa(text, openai_key):
+    llm = ChatOpenAI(openai_api_key=openai_key, max_tokens=2000, temperature=0.8)
+    prompt = ChatPromptTemplate.from_messages(
+        [
+            SystemMessagePromptTemplate.from_template(QA_gen_sys_prompt),
+            HumanMessagePromptTemplate.from_template(QA_gen_user_prompt),
+        ]
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    print('Generating Question from template')
+    qa = chain({'text': text})
+    result = json.loads(qa['text'])
+    return result
+
+
+def get_answer(context, question, openai_key):
+    llm = ChatOpenAI(openai_api_key=openai_key, max_tokens=2000, temperature=0.8)
+    prompt = ChatPromptTemplate.from_messages(
+        [
+            SystemMessagePromptTemplate.from_template(QA_answer_sys_prompt),
+            HumanMessagePromptTemplate.from_template(QA_answer_user_prompt),
+        ]
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    print('Generating Question from template')
+    answer = chain({'text': context, 'question': question})
+    answer = answer['text']
+    return answer

requirements.txt

@@ -0,0 +1,6 @@
+openai==0.27.2
+gradio==3.21.0
+langchain==0.0.113
+tiktoken==0.1.2
+sentence-transformers==2.2.2
+rouge_score