docs: updated tool info

README.md

@@ -44,11 +44,11 @@ Ragmint MCP Server exposes the full power of **Ragmint**, a modular Python libra
 
 ### Features exposed via MCP:
 
-* ✅ Automated hyperparameter optimization (Grid, Random, Bayesian via Optuna)
-* 🤖 Auto-RAG Tuner for dynamic retriever–embedding recommendations
-* 🧮 Validation QA generation for corpora without labeled data
-* 📦 Chunking, embeddings, retrievers, rerankers configuration
-* ⚙️ Full RAG pipeline control programmatically
+* ✅ Automated hyperparameter optimization (Grid, Random, Bayesian via Optuna).
+* 🤖 Auto-RAG Tuner for dynamic retriever–embedding recommendations.
+* 🧮 Validation QA generation for corpora without labeled data.
+* 📦 Chunking, embeddings, retrievers, rerankers configuration.
+* ⚙️ Full RAG pipeline control programmatically.
 
 ---
 
@@ -68,7 +68,7 @@ python app.py
 
 The server will expose MCP-compatible endpoints, allowing clients to:
 
-* Perform optimization experiments
+* Perform optimization experiments.
 * Automatically autotune pipelines.
 * Generate validation QA sets with LLM.
 
@@ -108,11 +108,13 @@ embedding_model: sentence-transformers/all-MiniLM-L6-v2
 
 ## 🔍 Supported Retrievers
 
-| Retriever    | Description                        |
-| ------------ | ---------------------------------- |
-| FAISS        | Fast vector similarity search      |
-| Chroma       | Persistent vector DB               |
-| scikit-learn | Local lightweight NearestNeighbors |
+| Retriever    | Description                                                      |
+|--------------|------------------------------------------------------------------|
+| FAISS        | Fast vector similarity search and indexing.                      |
+| Chroma       | Persistent vector database with embeddings.                      |
+| scikit-learn | Local lightweight NearestNeighbors retrieval.                    |
+| bm25         | Classical lexical search based on term relevance (TF-IDF-style). |
+| numpy        | Brute-force similarity search using raw vectors and matrix ops.  |
 
 ### Configuration Example
 
@@ -124,12 +126,12 @@ retriever: faiss
 
 ## 🧮 Dataset Options
 
-| Mode                 | Example                            | Description                                  |
-| -------------------- | ---------------------------------- | -------------------------------------------- |
-| Default              | validation_set=None                | Uses built-in experiments/validation_qa.json |
-| Custom File          | validation_set="data/my_eval.json" | Your QA dataset                              |
-| Hugging Face Dataset | validation_set="squad"             | Downloads benchmark dataset                  |
-
+| Mode                 | Example                            | Description                        |
+|----------------------|------------------------------------|------------------------------------|
+| Default              | validation_set=None                | Uses built-in validation_qa.json.  |
+| Custom File          | validation_set="data/my_eval.json" | Your QA dataset.                   |
+| Hugging Face Dataset | validation_set="squad"             | Downloads benchmark dataset.       |
+| Generate             | validation_set="generate"          | Generates the QA dataset with LLM. |
 
 ---
 
@@ -497,8 +499,8 @@ The Ragmint MCP Server exposes three main endpoints with the following example o
 ```
 </details>
 
-- **deleted_files**: Number of documents removed
-- **status**: "ok" indicates successful workspace reset
+- **deleted_files**: Number of documents removed.
+- **status**: "ok" indicates successful workspace reset.
 
 ---
 

app.py

@@ -25,7 +25,7 @@ def call_api(endpoint: str, payload: dict) -> str:
 
 def clear_cache_tool(docs_path="data/docs"):
     """
-    🧹 Clear Cache MCP Tool.
+    🗑️ Clear Cache MCP Tool.
 
     Deletes all files and directories inside docs_path on the server.
 
@@ -136,8 +136,8 @@ DEFAULT_AUTOTUNE_JSON = model_to_json(AutotuneRequest)
 DEFAULT_QA_JSON = model_to_json(QARequest)
 
 
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🤖 Ragmint MCP Server")
+with gr.Blocks(theme=gr.themes.Ocean()) as demo:
+    gr.Markdown("# 🧠 Ragmint MCP Server")
 
     gr.HTML("""
     <div style="display:flex; gap:5px; flex-wrap:wrap; align-items:center;">
@@ -163,35 +163,35 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     
     <br>
     
-    ## 🔧 MCP Tools (AI-Driven & Automated)
+    ## 🔧 MCP Tools
     
-    - 📄 **Upload Docs**: Upload .txt files to workspace for evaluation 
-    - 🔗 **Upload URLs**: Import remote .txt docs via URLs 
-    - 🧠 **Optimize RAG**: Full hyperparameter search (Grid / Random / Bayesian) with metrics 
-    - ⚙️ **Autotune RAG**: Automated recommendations for best chunking + embeddings 
-    - ❓ **Generate QA Dataset**: Create validation QA pairs with LLMs for benchmarking 
-    - 🧹 **Clear Cache**: Reset workspace and delete stored docs 
+    - 📄 **Upload Docs**: Upload .txt files to workspace for evaluation using `upload_docs`.
+    - 🔗 **Upload URLs**: Import remote docs via URLs with `upload_urls`.
+    - 🔧 **Optimize RAG**: Full hyperparameter search (Grid/Random/Bayesian) with metrics on `optimize_rag`.
+    - ⚡️ **Autotune RAG**: Automated recommendations for best chunking and embeddings with `autotune`.
+    - 🧩 **Generate QA Dataset**: Create validation QA pairs with LLMs for benchmarking using `generate_qa`.
+    - 🗑️ **Clear Cache**: Reset workspace and delete stored docs with `clear_cache`.
     
     <br>
     
     ## 🧠 What Ragmint Solves
     
-    - Automated RAG hyperparameter optimization
-    - Retriever, embedding, reranker selection
-    - Synthetic validation QA generation
-    - Evaluation metrics (faithfulness, latency, etc.)
-    - Experiment tracking & reproducible pipeline comparison
+    - Automated RAG hyperparameter optimization.
+    - Retriever, embedding, reranker selection.
+    - Synthetic validation QA generation.
+    - Evaluation metrics (faithfulness, latency, etc.).
+    - Experiment tracking & reproducible pipeline comparison.
     
     🔬 **Built for RAG engineers, researchers, and LLM developers** who want consistent performance improvement without trial-and-error.
     
     <br>
     
-    ## 🧠 Powered by
+    ## ⚙ Powered by
     
-    - **Optuna** (Bayesian Optimization)
-    - **Google Gemini 2.5 Flash Lite / Pro**
-    - **FAISS, Chroma, BM25, scikit-learn retrievers**
-    - **Sentence-Transformers / BGE embeddings**
+    - Optuna (Bayesian Optimization).
+    - Google Gemini 2.5 Flash Lite/Pro.
+    - FAISS, Chroma, BM25, scikit-learn retrievers.
+    - Sentence-Transformers/BGE embeddings.
     
     <br>
     
@@ -207,10 +207,10 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     
     ## 📦 Example MCP Use Cases
     
-    - 🧠 Run Auto-Optimization for RAG pipelines  
-    - 📊 Compare embedding + retriever combinations  
-    - ❓ Automatically generate QA validation datasets  
-    - 🔁 Rapid experiment iteration inside Claude / Cursor  
+    - Run Auto-Optimization for RAG pipelines.
+    - Compare embedding + retriever combinations.  
+    - Automatically generate QA validation datasets.
+    - Rapid experiment iteration inside Claude/Cursor.
     
     <br>
     
@@ -234,18 +234,17 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             # Upload Documents
             with gr.Column(scale=1):
                 gr.Markdown("## Upload Documents")
-                gr.Markdown("📂 Upload files (local paths or URLs) to your `data/docs` folder")
+                gr.Markdown("📄 Upload files (local paths or URLs) to your `data/docs` folder.")
                 upload_files = gr.File(file_count="multiple", type="filepath")
                 upload_path = gr.Textbox(value=DEFAULT_UPLOAD_PATH, label="Docs Path")
-                upload_btn = gr.Button("Upload", variant="primary")
+                upload_btn = gr.Button("Upload", variant="huggingface")
                 upload_out = gr.JSON(label="Response")
                 upload_btn.click(upload_docs_tool, inputs=[upload_files, upload_path], outputs=upload_out)
 
-
             # Upload MCP Documents (no file uploader)
             with gr.Column(scale=1):
                 gr.Markdown("## Upload Documents from URLs")
-                gr.Markdown("📂 Upload files (URLs) to your `data/docs` folder on MCP.")
+                gr.Markdown("🔗 Upload files (URLs) to your `data/docs` folder on MCP.")
 
                 upload_mcp_input = gr.TextArea(
                     placeholder="Paste URLs (one per line without commas)",
@@ -265,7 +264,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     return upload_docs_tool(urls, docs_path)
 
                 upload_mcp_path = gr.Textbox(value=DEFAULT_UPLOAD_PATH, label="Docs Path")
-                upload_mcp_btn = gr.Button("Upload", variant="primary")
+                upload_mcp_btn = gr.Button("Upload", variant="huggingface")
                 upload_mcp_out = gr.JSON(label="Response")
 
                 upload_mcp_btn.click(
@@ -323,7 +322,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     label="LLM Model"
                 )
 
-            autotune_btn = gr.Button("Autotune", variant="primary")
+            autotune_btn = gr.Button("Autotune", variant="huggingface")
             autotune_out = gr.Textbox(label="Response", lines=15)
 
 
@@ -433,7 +432,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     label="LLM Model"
                 )
 
-            optimize_btn = gr.Button("Optimize", variant="primary")
+            optimize_btn = gr.Button("Optimize", variant="huggingface")
             optimize_out = gr.Textbox(label="Response", lines=15)
 
 
@@ -497,7 +496,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     min_q = gr.Slider(1, 20, step=1, value=3, label="Min Questions")
                     max_q = gr.Slider(1, 50, step=1, value=25, label="Max Questions")
 
-                qa_btn = gr.Button("Generate QA", variant="primary")
+                qa_btn = gr.Button("Generate QA", variant="huggingface")
                 qa_out = gr.Textbox(lines=15, label="Response")
 
 
@@ -524,13 +523,13 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
 
                 gr.Markdown("---")
 
-    with gr.Tab("🧹 Clear Cache"):
+    with gr.Tab("🗑️ Clear Cache"):
         # Clear Cache
         with gr.Column():
             gr.Markdown("## Clear Cache")
-            gr.Markdown("🧹 Deletes all files and directories inside docs_path on the server.")
+            gr.Markdown("🗑️ Deletes all files and directories inside docs_path on the server.")
             clear_path = gr.Textbox(value=DEFAULT_UPLOAD_PATH, label="Docs Path to Clear")
-            clear_btn = gr.Button("Clear Cache", variant="primary")
+            clear_btn = gr.Button("Clear Cache", variant="huggingface")
             clear_out = gr.JSON(label="Response")
             clear_btn.click(clear_cache_tool, inputs=[clear_path], outputs=clear_out)
             gr.Markdown("---")