refactor: new gradio app

api.py

@@ -5,9 +5,10 @@ import logging
 import time
 
 from models import OptimizeRequest, QARequest, AutotuneRequest
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, UploadFile, File, Form
 from fastapi.middleware.cors import CORSMiddleware
 import uvicorn
+import shutil
 
 try:
     from ragmint.autotuner import AutoRAGTuner
@@ -56,6 +57,22 @@ def health():
     }
 
 
+@app.post("/upload_docs")
+async def upload_docs(
+    docs_path: str = Form(...),  # User specifies folder
+    files: list[UploadFile] = File(...)
+):
+    os.makedirs(docs_path, exist_ok=True)  # create folder if missing
+    saved_files = []
+
+    for file in files:
+        file_path = os.path.join(docs_path, file.filename)
+        with open(file_path, "wb") as f:
+            shutil.copyfileobj(file.file, f)
+        saved_files.append(file.filename)
+
+    return {"status": "ok", "uploaded_files": saved_files, "docs_path": docs_path}
+
 @app.post("/optimize_rag")
 def optimize_rag(req: OptimizeRequest):
     logger.info("Received optimize_rag request: %s", req.json())

app.py

@@ -1,50 +1,114 @@
 import gradio as gr
 import requests
 import json
-import server
+from models import OptimizeRequest, AutotuneRequest, QARequest
+import os
 
 API_URL = "http://localhost:8000"
 
-def optimize_rag_tool(payload: str) -> str:
-    """Run RAGMint full optimization workflow.
 
-    Args:
-        payload: JSON string containing OptimizeRequest parameters.
+# -------------------------------
+# Helper to call API
+# -------------------------------
+def call_api(endpoint: str, payload: dict) -> str:
+    try:
+        r = requests.post(f"{API_URL}/{endpoint}", json=payload)
+        return json.dumps(r.json(), indent=2)
+    except Exception as e:
+        return str(e)
 
-    Returns:
-        JSON result with best config and leaderboard stats.
-    """
-    r = requests.post(f"{API_URL}/optimize_rag", json=json.loads(payload))
-    return json.dumps(r.json(), indent=2)
 
-def autotune_tool(payload: str) -> str:
-    """Run AutoRAG tuner to recommend best configs and optimize.
+# -------------------------------
+# MCP Tool Wrappers
+# -------------------------------
+def upload_docs_tool(files, docs_path="data/docs"):
+
+    os.makedirs(docs_path, exist_ok=True)
+    uploaded_files = []
+
+    for file_path in files:
+        filename = os.path.basename(file_path)
+        dest_path = os.path.join(docs_path, filename)
+        import shutil
+        shutil.copy(file_path, dest_path)
+        uploaded_files.append(filename)
+
+    return {"status": "ok", "uploaded_files": uploaded_files, "docs_path": docs_path}
 
-    Args:
-        payload: JSON string for AutotuneRequest
 
-    Returns:
-        JSON result for tuning and full optimization.
-    """
-    r = requests.post(f"{API_URL}/autotune_rag", json=json.loads(payload))
-    return json.dumps(r.json(), indent=2)
+def optimize_rag_tool(payload: str) -> str:
+    return call_api("optimize_rag", json.loads(payload))
+
+
+def autotune_tool(payload: str) -> str:
+    return call_api("autotune_rag", json.loads(payload))
+
 
 def generate_qa_tool(payload: str) -> str:
-    """Generate validation QA set automatically with Gemini or Anthropic.
-
-    Args:
-        payload: JSON string for QARequest
-
-    Returns:
-        JSON preview of generated dataset
-    """
-    r = requests.post(f"{API_URL}/generate_validation_qa", json=json.loads(payload))
-    return json.dumps(r.json(), indent=2)
-
-demo = gr.Interface(
-    fn=optimize_rag_tool,
-    inputs=gr.Textbox(lines=12, label="OptimizeRequest JSON"),
-    outputs=gr.Textbox(label="Response")
-)
+    return call_api("generate_validation_qa", json.loads(payload))
+
+
+# -------------------------------
+# Generate default JSON for models
+# -------------------------------
+def model_to_json(model_cls) -> str:
+    defaults = {k: v.default for k, v in model_cls.__fields__.items()}
+    return json.dumps(defaults, indent=2)
+
+
+# Default payloads
+DEFAULT_UPLOAD_PATH = "data/docs"
+DEFAULT_UPLOAD_FILES = []  # No files by default
+DEFAULT_OPTIMIZE_JSON = model_to_json(OptimizeRequest)
+DEFAULT_AUTOTUNE_JSON = model_to_json(AutotuneRequest)
+DEFAULT_QA_JSON = model_to_json(QARequest)
+
+# -------------------------------
+# Build Gradio interface
+# -------------------------------
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# Ragmint MCP Client")
+
+    # Upload files section
+    with gr.Column():
+        gr.Markdown("## Upload Documents\nUpload files to a folder on the server.")
+        upload_files = gr.File(
+            file_types=[".txt", ".md", ".pdf"],  # allowed extensions
+            file_count="multiple",  # allow multiple files
+            type="filepath",  # returns local file path
+            label="Drag & Drop Files"
+        )
+        upload_path = gr.Textbox(value=DEFAULT_UPLOAD_PATH, label="Docs Path")
+        upload_output = gr.Textbox(label="Response")
+        upload_btn = gr.Button("Upload",variant='primary')
+        upload_btn.click(upload_docs_tool, inputs=[upload_files, upload_path], outputs=upload_output)
+        gr.Markdown("---")
+
+    # Optimize RAG
+    with gr.Column():
+        gr.Markdown("## Optimize RAG\nRun full RAG optimization with custom parameters.")
+        optimize_input = gr.Textbox(lines=12, value=DEFAULT_OPTIMIZE_JSON, label="OptimizeRequest JSON")
+        optimize_output = gr.Textbox(lines=15, label="Response")
+        optimize_btn = gr.Button("Submit",variant='primary')
+        optimize_btn.click(optimize_rag_tool, inputs=optimize_input, outputs=optimize_output)
+        gr.Markdown("---")
+
+    # Autotune RAG
+    with gr.Column():
+        gr.Markdown("## Autotune RAG\nRun AutoRAG tuner and full optimization.")
+        autotune_input = gr.Textbox(lines=12, value=DEFAULT_AUTOTUNE_JSON, label="AutotuneRequest JSON")
+        autotune_output = gr.Textbox(lines=15, label="Response")
+        autotune_btn = gr.Button("Submit",variant='primary')
+        autotune_btn.click(autotune_tool, inputs=autotune_input, outputs=autotune_output)
+        gr.Markdown("---")
+
+    # Generate QA
+    with gr.Column():
+        gr.Markdown("## Generate QA\nGenerate validation QA dataset from documents.")
+        qa_input = gr.Textbox(lines=12, value=DEFAULT_QA_JSON, label="QARequest JSON")
+        qa_output = gr.Textbox(lines=15, label="Response")
+        qa_btn = gr.Button("Submit",variant='primary')
+        qa_btn.click(generate_qa_tool, inputs=qa_input, outputs=qa_output)
+        gr.Markdown("---")
 
 demo.launch(mcp_server=True)