Update app.py

app.py

@@ -1,64 +1,48 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
+# openAI Model e openAI Embedings
 
+from langchain_community.document_loaders import UnstructuredMarkdownLoader
+from langchain_core.documents import Document
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain.chains import RetrievalQA
+from langchain.chat_models import init_chat_model
+import gradio as gr
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+llm = init_chat_model("gpt-4o-mini", model_provider="openai")
 
-    messages.append({"role": "user", "content": message})
+loader = UnstructuredMarkdownLoader("manual.md")
+documentos = loader.load()
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+textos = text_splitter.split_documents(documentos)
 
-    response = ""
+embeddings = OpenAIEmbeddings()
+db = Chroma.from_documents(textos, embeddings)
 
-    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
+retriever = db.as_retriever(search_kwargs={"k": 3})
 
-        response += token
-        yield response
+qa_chain = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=retriever,
+    verbose=True
+)
 
+def consultar_base_conhecimento(pergunta, history):
+    resposta = qa_chain.run(pergunta)
+    return resposta
 
+css = """
+footer { display: none !important; }
+.footer { display: none !important; } 
+.gradio-footer {  display: none !important;}" 
 """
-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(css=css) as demo:
+    demo = gr.ChatInterface(fn=consultar_base_conhecimento, title="Chatbot de Perguntas e Respostas", examples=["O que você sabe?", "Quem é o reitor?", "Como funciona o processo de matrícula?", "Como solicitar um histórico escolar?","Quais são as regras para aprovação nas disciplinas?"])
+    gr.HTML("<div style='text-align: center; width: 100%; margin-top: 10px; padding: 5px;'><p>O conteúdo gerado pode conter erros ou informações falsas.</p><p>© Construído por Giseldo Neo</p>")
 
+# Iniciar o aplicativo
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()