Update app.py

app.py

@@ -6,16 +6,16 @@ import numpy as np
 import json
 from sentence_transformers import SentenceTransformer
 
-# ✅ Load RAG-related files
+# ✅ Load data
 with open("texts.json", "r", encoding="utf-8") as f:
     texts = json.load(f)
 
 index = faiss.read_index("faiss_index.bin")
 embed_model = SentenceTransformer("all-MiniLM-L6-v2")
 
-# ✅ API setup
-API_KEY = os.environ.get("OPENROUTER_API_KEY")
-MODEL = "mistralai/mistral-7b-instruct:free"
+# ✅ Together AI Setup
+API_KEY = os.environ.get("TOGETHER_API_KEY") or "76615a7c686e20c0ee8cae288fddc7ab35ae51e768abc45b3defb5b1850d3dd0"
+MODEL = "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free"
 
 # ✅ Context retriever
 def get_context(query, top_k=5):
@@ -24,7 +24,7 @@ def get_context(query, top_k=5):
     context_chunks = [texts[i] for i in I[0] if i < len(texts)]
     return "\n".join(context_chunks).strip()
 
-# ✅ Chat function with strict context use
+# ✅ Chat function using Together API
 def chat_fn(message, history):
     context = get_context(message)
 
@@ -51,11 +51,13 @@ def chat_fn(message, history):
 
     payload = {
         "model": MODEL,
-        "messages": messages
+        "messages": messages,
+        "temperature": 0.7,
+        "max_tokens": 512
     }
 
     try:
-        response = requests.post("https://openrouter.ai/api/v1/chat/completions", headers=headers, json=payload)
+        response = requests.post("https://api.together.xyz/v1/chat/completions", headers=headers, json=payload)
         response.raise_for_status()
         reply = response.json()["choices"][0]["message"]["content"]
     except Exception as e:
@@ -63,7 +65,7 @@ def chat_fn(message, history):
 
     return reply
 
-# ✅ Gradio interface (clean look, no header/footer)
+# ✅ Gradio chat interface
 chat_ui = gr.ChatInterface(
     fn=chat_fn,
     title="",