Update README.md

README.md

@@ -41,11 +41,11 @@ This app uses:
 * **Large file handling**: If a file exceeds the soft cap, training will automatically use only the top 10K rows for processing
 * This optimization speeds up the training process and returns model IDs and responses faster
 
-### ✅ 1. Natural Chat Interface
+### 1. Natural Chat Interface
 
 Chat like a normal assistant — ask questions, discuss data, clarify tasks.
 
-### ✅ 2. Automatic CSV Analysis
+### 2. Automatic CSV Analysis
 
 Upload any structured CSV and ask:
 
@@ -59,7 +59,7 @@ The agent will produce:
 * Data quality issues
 * Recommendations
 
-### ✅ 3. One-Click Model Training
+### 3. Model Training
 
 Ask:
 
@@ -71,7 +71,7 @@ The agent will automatically:
 * Evaluate metrics (Accuracy, F1, ROC-AUC…)
 * Summarize key performance signals
 
-### ✅ 4. Automated Deployment
+### 4. Automated Deployment
 
 Ask:
 
@@ -83,7 +83,7 @@ The MCP backend handles deployment and returns:
 * Example Python inference code
 * Example curl usage
 
-### ✅ 5. Clean, Structured Responses
+### 5. Clean, Structured Responses
 
 Every response includes:
 
@@ -93,7 +93,7 @@ Every response includes:
 * Python + curl examples outside the collapsible
 * Tools, parameters, and logs inside a `<details>` block
 
-### ✅ 6. Full Streaming Output
+### 6. Full Streaming Output
 
 All assistant messages stream token-by-token for fast UX.
 
@@ -156,32 +156,6 @@ python app.py
 
 
 
-## ⚙️ Configuration
-
-### 🔧 Environment Variables
-
-| Variable         | Description                                                  |
-| - |  |
-| `OPENAI_API_KEY` | Your OpenAI key for GPT-5 / GPT-5-mini                       |
-| `MCP_SERVER_URL` | URL of the MCP backend handling analysis/training/deployment |
-
-### 🧩 Models
-
-You can change:
-
-```python
-MODEL = "gpt-5-mini"
-```
-
-to:
-
-```python
-MODEL = "gpt-5"
-```
-
-for stronger reasoning on tool outputs.
-
-
 
 ## 🧬 Architecture
 
@@ -195,60 +169,6 @@ User → Gradio Chat UI
 ```
 
 
-
-## 🧪 Example User Flow
-
-### 1️⃣ Upload CSV
-
-The app generates a public endpoint for the MCP tool to access.
-
-### 2️⃣ Ask:
-
-```
-Analyze this dataset
-```
-
-### 3️⃣ Ask:
-
-```
-Train a model
-```
-
-### 4️⃣ Ask:
-
-```
-Deploy the model
-```
-
-### 5️⃣ Use Example Code
-
-The assistant outputs example usable code:
-
-**Python**
-
-```python
-import requests
-url = "https://YOUR_ENDPOINT"
-payload = {...}
-print(requests.post(url, json=payload).json())
-```
-
-**curl**
-
-```bash
-curl -X POST https://YOUR_ENDPOINT -d '{...}'
-```
-
-
-## 📝 System Prompts
-
-The app uses two prompts:
-
-* **General Chat Prompt** — for simple conversations
-* **Main MLOps Prompt** — for analysis, training, evaluation & deployment
-
-Both enforce clean markdown, structured summaries, and technical transparency inside a collapsible block.
-
 ## 🛠️ Tech Stack
 
 * Python 3.10+