Update app.py

app.py

@@ -1,77 +1,17 @@
-import os
-import shutil
-import tempfile
-import gradio as gr
-
-from langchain_community.vectorstores import Chroma
-from langchain_community.document_loaders import PyPDFLoader, UnstructuredWordDocumentLoader
-from langchain_community.embeddings import HuggingFaceEmbeddings
-
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.chains import RetrievalQA
-from langchain.llms import LiteLLM
-
-DB_DIR = "chroma_db"
-CHUNK_SIZE = 500
-CHUNK_OVERLAP = 50
-
-def load_documents(file_path):
-    if file_path.endswith(".pdf"):
-        loader = PyPDFLoader(file_path)
-    elif file_path.endswith(".docx") or file_path.endswith(".doc"):
-        loader = UnstructuredWordDocumentLoader(file_path)
-    else:
-        raise ValueError("Unsupported file type. Only PDF and DOCX are supported.")
-    return loader.load()
-
-def create_vector_store(documents):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=CHUNK_SIZE, chunk_overlap=CHUNK_OVERLAP)
-    texts = text_splitter.split_documents(documents)
-
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
-    vectordb = Chroma.from_documents(texts, embedding=embeddings, persist_directory=DB_DIR)
-    vectordb.persist()
-    return vectordb
-
-def process_file(file):
-    temp_path = file.name
-    target_path = os.path.join(tempfile.gettempdir(), os.path.basename(temp_path))
-
-    if os.path.abspath(temp_path) != os.path.abspath(target_path):
-        shutil.copy(temp_path, target_path)
-
-    documents = load_documents(target_path)
-
-    if os.path.exists(DB_DIR):
-        shutil.rmtree(DB_DIR)
-
-    vectordb = create_vector_store(documents)
-    return "✅ تم معالجة الملف بنجاح. يمكنك الآن كتابة سؤالك."
-
-def ask_question(question):
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
-    vectordb = Chroma(persist_directory=DB_DIR, embedding_function=embeddings)
-
-    retriever = vectordb.as_retriever()
-
-    llm = LiteLLM(model="mistralai/Mistral-7B-Instruct-v0.2")  # لا حاجة لمفتاح API
-    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
-
-    result = qa_chain.run(question)
-    return result
-
-with gr.Blocks(title="Smart PDF Assistant") as demo:
-    gr.Markdown("### 🤖 مساعد الكتب الذكي - اسأل أي سؤال بناءً على ملف PDF أو DOCX")
-    
-    with gr.Row():
-        file_input = gr.File(label="📄 ارفع ملف PDF أو DOCX", file_types=[".pdf", ".docx", ".doc"])
-        file_status = gr.Textbox(label="حالة الملف", interactive=False)
-
-    with gr.Row():
-        question_input = gr.Textbox(label="❓ اكتب سؤالك هنا", placeholder="ما هو إيمان الكنيسة؟")
-        answer_output = gr.Textbox(label="📘 الإجابة", lines=8)
-
-    file_input.change(process_file, inputs=file_input, outputs=file_status)
-    question_input.submit(ask_question, inputs=question_input, outputs=answer_output)
-
-demo.launch()
+o install langchain-community run `pip install -U langchain-community`.
+  from langchain.llms import LiteLLM
+Traceback (most recent call last):
+  File "/home/user/app/app.py", line 12, in <module>
+    from langchain.llms import LiteLLM
+ImportError: cannot import name 'LiteLLM' from 'langchain.llms' (/usr/local/lib/python3.10/site-packages/langchain/llms/__init__.py)
+/home/user/app/app.py:12: LangChainDeprecationWarning: Importing LLMs from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
+
+`from langchain_community.llms import LiteLLM`.
+
+To install langchain-community run `pip install -U langchain-community`.
+  from langchain.llms import LiteLLM
+Traceback (most recent call last):
+  File "/home/user/app/app.py", line 12, in <module>
+    from langchain.llms import LiteLLM
+ImportError: cannot import name 'LiteLLM' from 'langchain.llms' (/usr/local/lib/python3.10/site-packages/langchain/llms/__init__.py)
+