Upload 3 files

README.md

@@ -1,14 +1,14 @@
----
-title: Brain247v1
-emoji: 🔥
-colorFrom: indigo
-colorTo: purple
-sdk: gradio
-sdk_version: 5.38.1
-app_file: app.py
-pinned: false
-license: mit
-short_description: brain
----
+# Smart PDF Assistant
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Upload PDF files and ask questions. Uses RAG with open-source models.
+
+### Features
+- Multilingual PDF support
+- Mistral 7B Instruct for Q&A
+- SentenceTransformers for embeddings
+- Exportable answers in Gradio
+
+## How to Use
+1. Upload your PDFs.
+2. Click "فهرسة الملفات".
+3. Ask any question and get a response.

app.py

@@ -0,0 +1,45 @@
+import os
+import gradio as gr
+from langchain.document_loaders import PyPDFLoader
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.llms import HuggingFaceHub
+from langchain.chains import RetrievalQA
+
+DB_DIR = "chroma_db"
+embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
+llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.2", model_kwargs={"temperature":0.3, "max_new_tokens":500})
+
+def load_and_index(files):
+    all_texts = []
+    for file in files:
+        loader = PyPDFLoader(file.name)
+        docs = loader.load()
+        splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        texts = splitter.split_documents(docs)
+        all_texts.extend(texts)
+    vectordb = Chroma.from_documents(all_texts, embedding=embedding_model, persist_directory=DB_DIR)
+    vectordb.persist()
+    return "✅ تم تحميل وفهرسة الملفات."
+
+def answer_question(query):
+    vectordb = Chroma(persist_directory=DB_DIR, embedding_function=embedding_model)
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=vectordb.as_retriever())
+    answer = qa_chain.run(query)
+    return answer
+
+with gr.Blocks(title="Smart PDF Assistant") as demo:
+    gr.Markdown("# 🤖 Smart PDF Assistant\nحمّل ملفات PDF واسأل أي سؤال 📚")
+    with gr.Row():
+        uploader = gr.File(file_types=[".pdf"], file_count="multiple", label="تحميل ملفات PDF")
+        index_btn = gr.Button("فهرسة الملفات")
+    index_output = gr.Textbox(label="حالة الفهرسة")
+    index_btn.click(load_and_index, inputs=[uploader], outputs=[index_output])
+
+    query = gr.Textbox(label="اكتب سؤالك")
+    answer_btn = gr.Button("أجب")
+    answer_output = gr.Textbox(label="الإجابة")
+    answer_btn.click(answer_question, inputs=[query], outputs=[answer_output])
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+langchain
+chromadb
+sentence-transformers
+pypdf
+huggingface_hub