Update app.py

app.py

@@ -1,17 +1,60 @@
-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)
- 
+import os
+import gradio as gr
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFaceHub
+from langchain.prompts import PromptTemplate
+from huggingface_hub import login
+
+# اختياري: تسجيل الدخول إذا كنت تستخدم مفتاح API
+# login(token="your_huggingface_token")
+
+def process_pdf_and_answer(pdf_path, question):
+    # تحميل ملف PDF
+    loader = PyPDFLoader(pdf_path)
+    pages = loader.load()
+
+    # تقسيم النصوص
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    texts = text_splitter.split_documents(pages)
+
+    # التضمين Embeddings
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
+    vectorstore = Chroma.from_documents(texts, embedding=embeddings)
+
+    # إعداد LLM
+    llm = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta", model_kwargs={"temperature": 0.1, "max_new_tokens": 512})
+
+    # إعداد RAG
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=vectorstore.as_retriever(), return_source_documents=True)
+
+    # تنفيذ السؤال
+    result = qa_chain({"query": question})
+    answer = result["result"]
+    return answer
+
+# واجهة Gradio
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 مساعد PDF الذكي")
+    
+    with gr.Row():
+        file_input = gr.File(label="📄 ارفع ملف PDF", type="filepath", file_types=[".pdf"])
+    
+    question_input = gr.Textbox(label="❓ اكتب سؤالك هنا", placeholder="ما هو محتوى الفصل الأول؟")
+    output = gr.Textbox(label="📝 الإجابة", lines=10)
+
+    submit_btn = gr.Button("🔍 استخرج الإجابة")
+
+    def handle_submit(file, question):
+        if file is None or question.strip() == "":
+            return "يرجى رفع ملف PDF وكتابة سؤال."
+        return process_pdf_and_answer(file, question)
+
+    submit_btn.click(handle_submit, inputs=[file_input, question_input], outputs=output)
+
+# لتشغيل التطبيق
+if __name__ == "__main__":
+    demo.launch()