Update app.py

app.py

@@ -1,76 +1,51 @@
-# Standard imports
-import os
-import sys
-import warnings
+import gradio as gr
+from api import get_all_questions, submit_answers, get_file
+from agent import answer_question
+from tools.file_loader import read_pdf, read_csv, read_txt
+
+qa_data = []
+answers = []
+
+def run_agent():
+    global qa_data, answers
+    qa_data = get_all_questions()
+    answers = []
+    for q in qa_data:
+        task_id = q['task_id']
+        question = q['question']
+        file_text = None
+        if q.get("files"):
+            for fname in q["files"]:
+                raw = get_file(task_id, fname)
+                if fname.endswith(".pdf"):
+                    file_text = read_pdf(raw)
+                elif fname.endswith(".csv"):
+                    file_text = read_csv(raw)
+                elif fname.endswith(".txt"):
+                    file_text = read_txt(raw)
+                break
+
+        response = answer_question(question, file_context=file_text, do_search=True)
+        answers.append({"task_id": task_id, "submitted_answer": response})
+    return f"Agent answered {len(answers)} questions. Ready to submit!"
+
+def handle_submit(username, code_link):
+    return submit_answers(username, code_link, answers)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# GAIA Level 1 Agent")
+
+    with gr.Row():
+        username = gr.Textbox(label="Hugging Face Username")
+        code_link = gr.Textbox(label="Space Code URL (/tree/main)")
+
+    status = gr.Textbox(label="Status", lines=4)
+
+    run_btn = gr.Button(" Run Agent")
+    submit_btn = gr.Button("Submit Answers")
+
+    run_btn.click(fn=run_agent, outputs=status)
+    submit_btn.click(fn=handle_submit, inputs=[username, code_link], outputs=status)
 
-# LangChain community imports (Updated for v0.2+)
-from langchain_community.document_loaders import TextLoader, PyPDFLoader, CSVLoader
-from langchain_community.embeddings import OpenAIEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.llms import OpenAI
-from langchain_community.tools import DuckDuckGoSearchRun
-
-# Other imports (you may have these depending on use)
-from langchain.chains import RetrievalQA
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.schema import Document
-
-# Add your environment key for OpenAI if required
-os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY", "your-api-key-here")
-
-def load_documents(directory: str):
-    """Loads documents from a directory using supported loaders."""
-    docs = []
-    for filename in os.listdir(directory):
-        filepath = os.path.join(directory, filename)
-        if filename.endswith(".txt"):
-            loader = TextLoader(filepath)
-        elif filename.endswith(".pdf"):
-            loader = PyPDFLoader(filepath)
-        elif filename.endswith(".csv"):
-            loader = CSVLoader(filepath)
-        else:
-            continue
-        docs.extend(loader.load())
-    return docs
-
-def build_vector_store(docs):
-    """Build FAISS index from documents using OpenAI embeddings."""
-    embeddings = OpenAIEmbeddings()
-    return FAISS.from_documents(docs, embeddings)
-
-def build_qa_chain(vectorstore):
-    """Create a RetrievalQA chain from the vector store."""
-    retriever = vectorstore.as_retriever()
-    llm = OpenAI(temperature=0)
-    return RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
-
-def main():
-    # Load and process data
-    data_path = "data/"  # Change to your actual directory
-    print("[INFO] Loading documents...")
-    documents = load_documents(data_path)
-
-    print("[INFO] Splitting text...")
-    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-    split_docs = splitter.split_documents(documents)
-
-    print("[INFO] Creating vector store...")
-    vectorstore = build_vector_store(split_docs)
-
-    print("[INFO] Building QA chain...")
-    qa_chain = build_qa_chain(vectorstore)
-
-    print("\n[READY] Ask questions (type 'exit' to quit):\n")
-    while True:
-        question = input("Q: ")
-        if question.lower() in ["exit", "quit"]:
-            print("Goodbye!")
-            break
-        answer = qa_chain.run(question)
-        print("A:", answer)
-
-# Main entry point
 if __name__ == "__main__":
-    warnings.filterwarnings("ignore", category=DeprecationWarning)
-    main()
+    demo.launch()