save

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+*.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,7 +4,7 @@ emoji: 🏢
 colorFrom: pink
 colorTo: purple
 sdk: gradio
-sdk_version: 3.28.0
+sdk_version: 3.27.0
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -0,0 +1,105 @@
+#!/usr/bin/python3
+import os
+from typing import Optional, Tuple
+
+import gradio as gr
+import pickle
+from query_data import get_chain
+from threading import Lock
+from langchain.vectorstores.faiss import FAISS
+from langchain.embeddings import OpenAIEmbeddings
+
+embeddings = OpenAIEmbeddings()
+vectorstore = FAISS.load_local('saved_model/vector.db',embeddings)
+
+def set_openai_api_key(api_key: str):
+    """Set the api key and return chain.
+    If no api_key, then None is returned.
+    """
+    if api_key:
+        os.environ["OPENAI_API_KEY"] = api_key
+        chain = get_chain(vectorstore)
+        os.environ["OPENAI_API_KEY"] = ""
+        return chain
+
+class ChatWrapper:
+
+    def __init__(self):
+        self.lock = Lock()
+    def __call__(
+        self, api_key: str, inp: str, history: Optional[Tuple[str, str]], chain
+    ):
+        """Execute the chat functionality."""
+        self.lock.acquire()
+        try:
+            history = history or []
+            # If chain is None, that is because no API key was provided.
+            if chain is None:
+                history.append((inp, "Please paste your OpenAI key to use"))
+                return history, history
+            # Set OpenAI key
+            import openai
+            openai.api_key = api_key
+            # Run chain and append input.
+            output = chain({"question": inp, "chat_history": history})["answer"]
+            history.append((inp, output))
+        except Exception as e:
+            raise e
+        finally:
+            self.lock.release()
+        return history, history
+
+chat = ChatWrapper()
+
+block = gr.Blocks(css=".gradio-container {background-color: lightgray}")
+
+with block:
+    with gr.Row():
+        gr.Markdown("<h3><center>CTM-GPT (中草藥資訊查詢小幫手)</center></h3><br/><center>Author: markchiang</center>")
+
+        openai_api_key_textbox = gr.Textbox(
+            placeholder="Paste your OpenAI API key (sk-...)",
+            show_label=False,
+            lines=1,
+            type="password",
+        )
+
+    chatbot = gr.Chatbot()
+
+    with gr.Row():
+        message = gr.Textbox(
+            label="What's your question?",
+            placeholder="問中草藥相關的問題",
+            lines=1,
+        )
+        submit = gr.Button(value="Send", variant="secondary").style(full_width=False)
+
+    gr.Examples(
+        examples=[
+            "癌症相關的中草藥",
+            "七寶美髯丹有哪些成分?",
+            "麻黃湯每種成分各有多少量?",
+            "鬚髮早白可以用什麼藥方?",
+        ],
+        inputs=message,
+    )
+
+    gr.HTML("Demo application of TCM helper.")
+
+    gr.HTML(
+            "<center>Author: markchiang<br/>Powered by OpenAI and Gradio. </center>"
+    )
+
+    state = gr.State()
+    agent_state = gr.State()
+
+    submit.click(chat, inputs=[openai_api_key_textbox, message, state, agent_state], outputs=[chatbot, state])
+    message.submit(chat, inputs=[openai_api_key_textbox, message, state, agent_state], outputs=[chatbot, state])
+
+    openai_api_key_textbox.change(
+        set_openai_api_key,
+        inputs=[openai_api_key_textbox],
+        outputs=[agent_state],
+    )
+
+block.launch(debug=True)

query_data.py

@@ -0,0 +1,35 @@
+from langchain.prompts.prompt import PromptTemplate
+from langchain.llms import OpenAI
+from langchain.chains import ChatVectorDBChain
+
+_template = """鑑於以下對話和後續問題，將後續問題改寫為獨立問題。
+您可以假設這是有關中草藥和疾病與健康相關的問題。
+
+Chat History:
+{chat_history}
+Follow Up Input: {question}
+Standalone question:"""
+CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)
+
+template = """你是一名 AI 助手，負責回答有關中草藥與健康相關的問題。
+您將獲得一份長文檔的以下提取部分和一個問題。 提供對話答案。
+如果你不知道答案，就說“我不確定。” 不要試圖編造答案。
+如果問題不是關於中草藥與疾病健康的知識，請禮貌地告訴他們你只能回答關於中草藥相關的問題。
+Question: {question}
+=========
+{context}
+=========
+Answer in Markdown:"""
+QA_PROMPT = PromptTemplate(template=template, input_variables=["question", "context"])
+
+
+def get_chain(vectorstore):
+    llm = OpenAI(temperature=0,model_name="gpt-4")
+    qa_chain = ChatVectorDBChain.from_llm(
+        llm,
+        vectorstore,
+#        qa_prompt=QA_PROMPT,
+        condense_question_prompt=CONDENSE_QUESTION_PROMPT,
+        return_source_documents=True
+    )
+    return qa_chain

requirements.txt

@@ -0,0 +1,7 @@
+pip==23.1
+langchain==0.0.148
+openai==0.27.2
+unstructured==0.6.1
+faiss-cpu==1.7.4
+gradio==3.27.0
+tiktoken

saved_model/vector.db/.gitattributes

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2446fde201f48768a639ed346a65d5e8c17f69bd0aa0109b11694eb3c4bb2056
+size 44

saved_model/vector.db/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b0600d3913cda0bd7e6f857a359467b237e464b228242c630dd1ef82fa41d2
+size 10371117

saved_model/vector.db/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906b9a352f805c3c671bbfb75470a39ae0dbd02d093991112d357a8ecd7b11d0
+size 3201973