Update app.py

app.py

@@ -1,64 +1,73 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_core.vectorstores import InMemoryVectorStore
+from langchain.chains import RetrievalQA
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_groq import ChatGroq
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+model_name = "llama-3.3-70b-versatile"
+embeddings = HuggingFaceEmbeddings(
+    model_name = "pkshatech/GLuCoSE-base-ja"
+)
+vector_store = InMemoryVectorStore.load(
+    "kaihatsu_vector_store", embeddings
+)
+retriever = vector_store.as_retriever(search_kwargs={"k": 4})
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+def fetch_response(groq_api_key, user_input):
+  chat = ChatGroq(
+    api_key = groq_api_key,
+    model_name = model_name
+  )
+  system_prompt = (
+    "あなたは便利なアシスタントです。"
+    "マニュアルの内容から回答してください。"
+    "\n\n"
+    "{context}"
+    )
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+  prompt = ChatPromptTemplate.from_messages(
+      [
+          ("system", system_prompt),
+           ("human", "{input}"),
+          ]
+      )
+  # ドキュメントのリストを渡せるchainを作成
+  question_answer_chain = create_stuff_documents_chain(chat, prompt)
+  # RetrieverとQAチェーンを組み合わせてRAGチェーンを作成
+  rag_chain = create_retrieval_chain(retriever, question_answer_chain)
 
-        response += token
-        yield response
+  response = rag_chain.invoke({"input": user_input})
+  return [response["answer"], response["context"][0], response["context"][1]]
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+with gr.Blocks() as demo:
+    gr.Markdown('''# 「スマート農業技術の開発・供給に関する事業」マスター \n
+                     「スマート農業技術の開発・供給に関する事業」に関して、公募要領や審査要領を参考にRAGを使って回答します。
+                ''')
+    with gr.Row():
+        api_key = gr.Textbox(label="Groq API key")
+    with gr.Row():
+        with gr.Column():
+            user_input = gr.Textbox(label="User Input")
+            submit = gr.Button("Submit")
+            answer = gr.Textbox(label="Answer")
+    with gr.Row():
+        with gr.Column():
+            source1 = gr.Textbox(label="回答ソース１")
+        with gr.Column():
+            source2 = gr.Textbox(label="回答ソース２")
+    submit.click(fetch_response, inputs=[api_key, user_input], outputs=[answer, source1, source2])
 
 if __name__ == "__main__":
     demo.launch()