Create app.py

app.py

@@ -0,0 +1,29 @@
+from datetime import date, timedelta
+from langchain.document_loaders import ArxivLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+
+def get_data(user_query: str, load_max_docs: int = 5, chunk_size: int=1000):
+    min_date = (date.today() - timedelta(days=2)).strftime('%Y%m%d')
+    max_date = date.today().strftime('%Y%m%d')
+    query = f"cat:hep-th AND submittedDate:[{min_date.strftime('%Y%m%d')} TO {max_date.strftime('%Y%m%d')}]"
+    loader = ArxivLoader(query=query, load_max_docs=load_max_docs)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size)
+    texts = text_splitter.split_documents(documents)    
+    embeddings = HuggingFaceEmbeddings()    
+    db = FAISS.from_documents(texts, embeddings)
+    retriever = db.as_retriever()    
+    docs = retriever.get_relevant_documents(user_query)
+    print(docs[0].metadata)
+    return "\n\n".join([d.page_content for d in docs])
+
+demo = gr.Interface(
+    fn=get_data,
+    inputs="text",
+    outputs="text",
+    title="Document Filter",
+    description="Enter a query to filter the list of documents."
+)
+demo.queue().launch()