swap model

README.md

@@ -148,20 +148,54 @@ The chatbot uses Hugging Face Inference API to access high-quality models. You n
    - Add a new secret: Name = `HF_TOKEN`, Value = your token
    - The app will automatically use this token
 
-### Chatbot Model
+### Chatbot Model and Finding Available Models
 
-The chatbot uses **Mistral-7B-Instruct-v0.2** via Hugging Face Inference API. This is an instruction-tuned model that provides high-quality, coherent answers.
+The chatbot uses the Hugging Face Inference API. **Which models you can use depends on which providers you have enabled.**
 
-To change the model, edit `app.py`:
+**How to see which models are available to you:**
 
-```python
-chatbot = RAGChatbot(model_name="mistralai/Mistral-7B-Instruct-v0.2")
-```
+1. **Browse models that support Inference API**
+   - https://huggingface.co/inference/models — lists providers and models
+   - https://huggingface.co/models?inference_provider=hf-inference — filter Hub models by “HF Inference API”
+
+2. **Enable providers (required)**  
+   See **“How to enable a provider and model”** below.
+
+3. **Pick a chat model**
+   - From the links above, choose a **text generation / chat** model that’s supported by a provider you enabled. Note its **model id** (e.g. `meta-llama/Llama-3.2-1B-Instruct`).
+
+4. **Use it in the app**
+   - In `app.py`, pass that model id when creating the chatbot:
+   ```python
+   chatbot = RAGChatbot(model_name="meta-llama/Llama-3.2-1B-Instruct")  # use an id you enabled
+   ```
+   - The app also tries fallbacks (Phi-2, Zephyr, Qwen) by default; if none are available, enable a provider that supports at least one of them, or set `model_name` to a model you enabled as above.
+
+### How to enable a provider and model
+
+1. **Log in** to [Hugging Face](https://huggingface.co).
+
+2. **Open Inference Provider settings** (one of these, depending on the current UI):
+   - https://huggingface.co/settings/inference-providers  
+   - https://huggingface.co/settings/inference-api  
+
+3. **Enable a provider**
+   - On that page you’ll see a list of **providers** (e.g. Hugging Face, Together, Groq, etc.).
+   - **Turn on** the provider that serves your model (e.g. **Together** for `ServiceNow-AI/Apriel-1.6-15b-Thinker:together`).
+   - You can set the **order** of providers; “auto” uses this order to pick which provider handles the request.
+
+4. **Credits / billing**
+   - Free accounts get a small amount of monthly credits; usage is deducted from that.
+   - If you use a third-party provider (e.g. Together), you can either use HF-routed billing (credits on your HF account) or add a **custom provider API key** (e.g. Together API key) in the same settings so that provider is billed directly.
+
+5. **Confirm the model**
+   - Browse models for that provider:  
+     [Together models on the Hub](https://huggingface.co/models?inference_provider=together&sort=trending)  
+   - Open the model page (e.g. `ServiceNow-AI/Apriel-1.6-15b-Thinker`) and check the inference widget; if you see “Together” and can run it, that model is available with your enabled provider.
 
-Other recommended instruction-tuned models:
-- `HuggingFaceH4/zephyr-7b-beta` - Excellent for chat
-- `meta-llama/Meta-Llama-3-8B-Instruct` - High quality (requires access)
-- `microsoft/phi-2` - Smaller, faster option
+6. **Use it in this app**
+   - The app default is already `ServiceNow-AI/Apriel-1.6-15b-Thinker:together`.  
+   - Ensure **Together** is enabled in your Inference Provider settings and you have credits (or a Together API key). Then restart the app and send a message.
 
 ### Embedding Model
 

app.py

@@ -87,11 +87,11 @@ class RAGChatbot:
     """Chatbot with RAG capabilities."""
     
     # Default and fallback models (try in order until one is supported by your Inference API providers)
-    DEFAULT_CHAT_MODEL = "microsoft/phi-2"
+    DEFAULT_CHAT_MODEL = "Qwen/Qwen2.5-Coder-7B-Instruct"
     FALLBACK_CHAT_MODELS = [
+        "ServiceNow-AI/Apriel-1.6-15b-Thinker:together",
+        "microsoft/phi-2",
         "HuggingFaceH4/zephyr-7b-beta",
-        "Qwen/Qwen2-7B-Instruct",
-        "google/gemma-2-2b-it",
     ]
 
     def __init__(
@@ -234,9 +234,11 @@ Answer:"""
                         err_str = str(api_error).lower()
                         if "model_not_supported" in err_str or "not supported by any provider" in err_str:
                             return (
-                                "None of the configured chat models are available with your Inference API providers. "
-                                "Enable a provider for at least one supported model (e.g. Phi-2, Zephyr, Qwen) at "
-                                "https://huggingface.co/settings/inference-api."
+                                "None of the configured chat models are available with your Inference API providers.\n\n"
+                                "**How to fix:**\n"
+                                "1. See which models are available: https://huggingface.co/inference/models\n"
+                                "2. Enable providers (and pick a chat model): https://huggingface.co/settings/inference-api\n"
+                                "3. In app.py, set RAGChatbot(model_name=\"your-chosen-model-id\") to match a model you enabled."
                             )
                         # Fallback: return formatted chunks with note
                         response_parts = []