Duplicate from ducknew/MedKBQA

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+cache/index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: MedKBQA
+emoji: 💯
+colorFrom: pink
+colorTo: red
+sdk: gradio
+sdk_version: 3.28.3
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: ducknew/MedKBQA
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,156 @@
+import os
+import time
+import gradio as gr
+from tqdm import tqdm
+from loguru import logger
+from transformers import AutoTokenizer,AutoModel
+from duckduckgo_search import ddg_suggestions
+from duckduckgo_search import ddg_translate, ddg, ddg_news
+
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.text_splitter import CharacterTextSplitter,RecursiveCharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.schema import Document
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import ConversationalRetrievalChain,RetrievalQA
+from langchain.prompts import PromptTemplate
+from langchain.prompts.prompt import PromptTemplate
+from langchain.chat_models import ChatOpenAI
+
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).quantize(bits=4, compile_parallel_kernel=True, parallel_num=2).float()
+model = model.eval()
+
+
+def chat_glm(input, history=None):
+    if history is None:
+        history = []
+    response, history = model.chat(tokenizer, input, history)
+    logger.info("chatglm:", input,response)
+    return history, history
+
+def search_web(query):
+    logger.info("searchweb:", query)
+    results = ddg(query)
+    web_content = ''
+    if results:
+        for result in results:
+            web_content += result['body']
+    return web_content
+
+def chat_gpt(input, use_web, history=None):
+    if history is None:
+        history = []
+    embedding_model_name = 'GanymedeNil/text2vec-large-chinese'
+    vec_path = 'cache'
+    embeddings = HuggingFaceEmbeddings(model_name=embedding_model_name)
+
+    if use_web:
+        web_content = search_web(query)
+    else:
+        web_content = None
+    if web_content:
+        prompt_template = f"""基于以下已知信息，简洁和专业的来回答用户的问题。
+                            如果无法从中得到答案，请说 "根据已知信息无法回答该问题" 或 "没有提供足够的相关信息"，不允许在答案中添加编造成分，答案请使用中文。
+                            已知网络检索内容：{web_content}""" + """
+                            已知内容:
+                            {context}
+                            问题:
+                            {question}"""
+    else:
+        prompt_template = """基于以下已知信息，请简洁并专业地回答用户的问题。
+            如果无法从中得到答案，请说 "根据已知信息无法回答该问题" 或 "没有提供足够的相关信息"。不允许在答案中添加编造成分。另外，答案请使用中文。
+            已知内容:
+            {context}
+            问题:
+            {question}"""
+            
+    prompt = PromptTemplate(template=prompt_template,input_variables=["context", "question"])
+    vector_store = FAISS.load_local(vec_path,embeddings)
+
+    qa = RetrievalQA.from_llm(
+        llm = ChatOpenAI(temperature=0.7,model_name='gpt-3.5-turbo'),
+        retriever = vector_store.as_retriever(search_kwargs={"k": 3}),
+        prompt = prompt,
+        return_source_documents=True
+    )
+    
+    result = qa({"query": query, "chat_history": history})
+    logger.info("chatgpt:", input,result)
+    return result["answer"]
+
+def predict(input,
+            large_language_model,
+            use_web,
+            openai_key,
+            history=None):
+    logger.info("predict..",large_language_model,use_web)
+    if openai_key is not None:
+        os.environ['OPENAI_API_KEY'] = openai_key
+    else:
+        return '',"You forgot OpenAI API key","You forgot OpenAI API key"
+    if history == None:
+        history = []
+
+    if large_language_model == "gpt-3.5-turbo":
+        resp  = chat_gpt(input, use_web, history)
+    elif large_language_model == "ChatGLM-6B-int4":
+        resp = chat_glm(input, history)
+
+    history.append((input, resp))
+    return '', history, history
+
+def clear_session():
+    return '', None
+
+block = gr.Blocks()
+with block as demo:
+    gr.Markdown("""<h1><center>MedKBQA（demo）</center></h1>
+    <center><font size=3>
+    本项目基于LangChain、ChatGLM以及Open AI接口, 提供基于本地医药知识的自动问答应用. <br>
+    </center></font>
+    """)
+    with gr.Row():
+        with gr.Column(scale=1):
+            model_choose = gr.Accordion("模型选择")
+            with model_choose:
+                large_language_model = gr.Dropdown(
+                    ["ChatGLM-6B-int4","gpt-3.5-turbo"],
+                    label="large language model",
+                    value="ChatGLM-6B-int4")
+            use_web = gr.Radio(["True", "False"],
+                    label="Web Search",
+                    value="False")
+            openai_key = gr.Textbox(label="请输入OpenAI API key", type="password")
+        with gr.Column(scale=4):
+            chatbot = gr.Chatbot(label='ChatLLM').style(height=600)
+            message = gr.Textbox(label='请输入问题')
+            state = gr.State()
+
+            with gr.Row():
+                clear_history = gr.Button("🧹 清除历史对话")
+                send = gr.Button("🚀 发送")
+
+                send.click(predict,
+                           inputs=[
+                               message, large_language_model, use_web, openai_key, state
+                           ],
+                           outputs=[message, chatbot, state])
+                clear_history.click(fn=clear_session,
+                                    inputs=[],
+                                    outputs=[chatbot, state],
+                                    queue=False)
+
+                message.submit(predict,
+                               inputs=[
+                                   message, large_language_model, use_web, openai_key, state
+                               ],
+                               outputs=[message, chatbot, state])
+    gr.Markdown("""提醒：<br>
+    1. 使用时请先选择使用chatglm或者chatgpt进行问答. <br>
+    2. 使用chatgpt时需要输入您的api key.
+    """)
+demo.queue().launch(server_name='0.0.0.0', share=False)

cache/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3bddc5b874aec3b07d734adf6253f53c490570c3c00927d8d77ca12251eb91
+size 91779117

cache/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3171eebfa281ad94146ac42f6e0263c6b7e9a26de0616fb631253cf1d4d4df
+size 2297073

requirements.txt

@@ -0,0 +1,11 @@
+gradio
+torch
+transformers>=4.27.1
+cpm_kernels
+icetk
+dynaconf
+duckduckgo_search
+faiss-cpu
+sentence-transformers
+langchain
+loguru

setting.toml

@@ -0,0 +1,37 @@
+[models]
+
+        [models.llm."chatglm-6b"]
+            type = "chatglm"
+            path = "THUDM/chatglm-6b"
+        [models.llm."chatglm-6b-int8"]
+            type = "chatglm"
+            path = "THUDM/chatglm-6b-int8"
+        [models.llm."chatglm-6b-int4"]
+            type = "chatglm"
+            path = "THUDM/chatglm-6b-int4"
+        [models.llm."phoenix-inst-chat-7b"]
+            type = "phoenix"
+            path = "FreedomIntelligence/phoenix-inst-chat-7b"
+        [models.llm."phoenix-inst-chat-7b-int4"]
+            type = "phoenix"
+            path = "FreedomIntelligence/phoenix-inst-chat-7b-int4"
+
+    [models.embeddings]
+        [models.embeddings."text2vec-large-chinese"]
+            type = "default"
+            path = "GanymedeNil/text2vec-large-chinese"
+        [models.embeddings."text2vec-base"]
+            type = "default"
+            path = "shibing624/text2vec-base-chinese"
+        [models.embeddings."text2vec-base"]
+            type = "default"
+            path = "shibing624/text2vec-base-chinese"
+        [models.embeddings."sentence-transformers"]
+            type = "default"
+            path = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+        [models.embeddings."ernie-tiny"]
+            type = "default"
+            path = "nghuyong/ernie-3.0-nano-zh"
+        [models.embeddings."ernie-base"]
+            type = "default"
+            path = "nghuyong/ernie-3.0-base-zh"