update app

app.py

@@ -1,123 +1,132 @@
-import os
-import gradio as gr
-from typing import List
-from llama_index.core import SimpleDirectoryReader, StorageContext, VectorStoreIndex
-from llama_index.core.node_parser import SentenceSplitter
-from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.vector_stores.chroma import ChromaVectorStore
-from llama_index.llms.groq import Groq
-from llama_index.core.memory import ChatSummaryMemoryBuffer
-import chromadb
-from tempfile import TemporaryDirectory
-from PyPDF2 import PdfReader
-from corretor import corrigir_texto  # <<< Correção importada aqui
-
-# Wrapper de embedding compatível com ChromaDB
-class ChromaEmbeddingWrapper:
-    def __init__(self, model_name: str):
-        self.model = HuggingFaceEmbedding(model_name=model_name)
-
-    def __call__(self, input: List[str]) -> List[List[float]]:
-        return self.model.embed_documents(input)
-
-# Inicializa modelos de embedding
-embed_model = HuggingFaceEmbedding(model_name='intfloat/multilingual-e5-large')
-embed_model_chroma = ChromaEmbeddingWrapper(model_name='intfloat/multilingual-e5-large')
-
-# Inicializa ChromaDB
-chroma_client = chromadb.PersistentClient(path='./chroma_db')
-collection_name = 'documentos_bitdoglab'
-chroma_collection = chroma_client.get_or_create_collection(
-    name=collection_name,
-    embedding_function=embed_model_chroma
-)
-
-vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
-storage_context = StorageContext.from_defaults(vector_store=vector_store)
-
-# Inicializa LLM da Groq
-Groq_api = os.environ.get("GROQ_API_KEY")
-llms = Groq(model='llama3-70b-8192', api_key=Groq_api or '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')
-
-# Estados globais
-document_index = None
-chat_engine = None
-
-# Carregamento único do PDF
-def carregar_pdf_inicial():
-    global document_index, chat_engine
-
-    try:
-        with TemporaryDirectory() as tmpdir:
-            pdf_path = "BitDogLab_info_v2.pdf"
-            text = ""
-            reader = PdfReader(pdf_path)
-            for page in reader.pages:
-                text += page.extract_text() or ""
-
-            with open(os.path.join(tmpdir, "temp.txt"), "w", encoding="utf-8") as f:
-                f.write(text)
-
-            documentos = SimpleDirectoryReader(input_dir=tmpdir)
-            docs = documentos.load_data()
-
-            node_parser = SentenceSplitter(chunk_size=1200,chunk_overlap=150)
-            nodes = node_parser.get_nodes_from_documents(docs, show_progress=True)
-
-            document_index = VectorStoreIndex(nodes, storage_context=storage_context, embed_model=embed_model)
-
-            memory = ChatSummaryMemoryBuffer(llm=llms, token_limit=256)
-
-            chat_engine = document_index.as_chat_engine(
-                chat_mode='context',
-                llm=llms,
-                memory=memory,
-                system_prompt='''Você é especialista na placa BitDog Lab e sua função é ajudar os usuários nas dúvidas e informações sobre a placa e como criar códigos.'''
-            )
-
-            print("PDF carregado com sucesso.")
-
-    except Exception as e:
-        print(f"Erro ao carregar PDF: {e}")
-
-# Função de chat com correção de texto
-def converse_com_bot(message, chat_history):
-    global chat_engine
-
-    if chat_engine is None:
-        return "Erro: o bot ainda não está pronto.", chat_history
-
-    response = chat_engine.chat(message)
-    resposta_corrigida = corrigir_texto(response.response)  # <<< Aplica correção
-
-    if chat_history is None:
-        chat_history = []
-
-    chat_history.append({"role": "user", "content": message})
-    chat_history.append({"role": "assistant", "content": resposta_corrigida})
-
-    return "", chat_history
-
-# Resetar conversa
-def resetar_chat():
-    global chat_engine
-    if chat_engine:
-        chat_engine.reset()
-    return []
-
-# Carregar PDF na inicialização
-carregar_pdf_inicial()
-
-# Interface Gradio
-with gr.Blocks() as app:
-    gr.Markdown("# 🤖  Chatbot BitDog Lab - Seu assistente para esclarecer dúvidas")
-
-    chatbot = gr.Chatbot(label="Conversa", type="messages")
-    msg = gr.Textbox(label='Digite a sua mensagem')
-    limpar = gr.Button('Limpar')
-
-    msg.submit(converse_com_bot, [msg, chatbot], [msg, chatbot])
-    limpar.click(resetar_chat, None, chatbot, queue=False)
-
-    #app.launch()
-    app.launch(server_name="0.0.0.0", server_port=7860)
+import os
+import gradio as gr
+from typing import List
+from llama_index.core import SimpleDirectoryReader, StorageContext, VectorStoreIndex
+from llama_index.core.node_parser import SentenceSplitter
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.vector_stores.chroma import ChromaVectorStore
+from llama_index.llms.groq import Groq
+from llama_index.core.memory import ChatSummaryMemoryBuffer
+import chromadb
+from tempfile import TemporaryDirectory
+from PyPDF2 import PdfReader
+from corretor import corrigir_texto  # <<< Correção importada aqui
+import platform
+
+# Wrapper de embedding compatível com ChromaDB
+class ChromaEmbeddingWrapper:
+    def __init__(self, model_name: str):
+        self.model = HuggingFaceEmbedding(model_name=model_name)
+
+    def __call__(self, input: List[str]) -> List[List[float]]:
+        return self.model.embed_documents(input)
+
+# Inicializa modelos de embedding
+embed_model = HuggingFaceEmbedding(model_name='intfloat/multilingual-e5-large')
+embed_model_chroma = ChromaEmbeddingWrapper(model_name='intfloat/multilingual-e5-large')
+
+# Inicializa ChromaDB
+
+# Define caminho seguro dependendo do sistema operacional
+if platform.system() == "Windows":
+    chroma_path = "./chroma_db"
+else:
+    chroma_path = "/tmp/chroma_db"
+
+chroma_client = chromadb.PersistentClient(path=chroma_path)
+
+collection_name = 'documentos_bitdoglab'
+chroma_collection = chroma_client.get_or_create_collection(
+    name=collection_name,
+    embedding_function=embed_model_chroma
+)
+
+vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# Inicializa LLM da Groq
+Groq_api = os.environ.get("GROQ_API_KEY")
+llms = Groq(model='llama3-70b-8192', api_key=Groq_api or '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')
+
+# Estados globais
+document_index = None
+chat_engine = None
+
+# Carregamento único do PDF
+def carregar_pdf_inicial():
+    global document_index, chat_engine
+
+    try:
+        with TemporaryDirectory() as tmpdir:
+            pdf_path = "BitDogLab_info_v2.pdf"
+            text = ""
+            reader = PdfReader(pdf_path)
+            for page in reader.pages:
+                text += page.extract_text() or ""
+
+            with open(os.path.join(tmpdir, "temp.txt"), "w", encoding="utf-8") as f:
+                f.write(text)
+
+            documentos = SimpleDirectoryReader(input_dir=tmpdir)
+            docs = documentos.load_data()
+
+            node_parser = SentenceSplitter(chunk_size=1200,chunk_overlap=150)
+            nodes = node_parser.get_nodes_from_documents(docs, show_progress=True)
+
+            document_index = VectorStoreIndex(nodes, storage_context=storage_context, embed_model=embed_model)
+
+            memory = ChatSummaryMemoryBuffer(llm=llms, token_limit=256)
+
+            chat_engine = document_index.as_chat_engine(
+                chat_mode='context',
+                llm=llms,
+                memory=memory,
+                system_prompt='''Você é especialista na placa BitDog Lab e sua função é ajudar os usuários nas dúvidas e informações sobre a placa e como criar códigos.'''
+            )
+
+            print("PDF carregado com sucesso.")
+
+    except Exception as e:
+        print(f"Erro ao carregar PDF: {e}")
+
+# Função de chat com correção de texto
+def converse_com_bot(message, chat_history):
+    global chat_engine
+
+    if chat_engine is None:
+        return "Erro: o bot ainda não está pronto.", chat_history
+
+    response = chat_engine.chat(message)
+    resposta_corrigida = corrigir_texto(response.response)  # <<< Aplica correção
+
+    if chat_history is None:
+        chat_history = []
+
+    chat_history.append({"role": "user", "content": message})
+    chat_history.append({"role": "assistant", "content": resposta_corrigida})
+
+    return "", chat_history
+
+# Resetar conversa
+def resetar_chat():
+    global chat_engine
+    if chat_engine:
+        chat_engine.reset()
+    return []
+
+# Carregar PDF na inicialização
+carregar_pdf_inicial()
+
+# Interface Gradio
+with gr.Blocks() as app:
+    gr.Markdown("# 🤖  Chatbot BitDog Lab - Seu assistente para esclarecer dúvidas")
+
+    chatbot = gr.Chatbot(label="Conversa", type="messages")
+    msg = gr.Textbox(label='Digite a sua mensagem')
+    limpar = gr.Button('Limpar')
+
+    msg.submit(converse_com_bot, [msg, chatbot], [msg, chatbot])
+    limpar.click(resetar_chat, None, chatbot, queue=False)
+
+    #app.launch()
+    app.launch(server_name="0.0.0.0", server_port=7860)