Update app.py

app.py

@@ -75,25 +75,28 @@ from qdrant_client.models import VectorParams, Distance
 from langchain.llms import HuggingFacePipeline
 from langchain.chains import RetrievalQA
 from langchain.vectorstores import Qdrant
-from transformers import GenerationConfig, FastLanguageModel
+from transformers import GenerationConfig, AutoTokenizer, AutoModelForCausalLM
 from langchain.embeddings import HuggingFaceEmbeddings
+import os
+
+QDRANT_API_KEY = os.getenv("QDRANT_API_KEY")
+QDRANT_URL = os.getenv("QDRANT_URL")
+
+
+
 
 # Define model path
 model_name = "FreedomIntelligence/Apollo-7B"
 
-# Load model with Unsloth (4-bit QLoRA)
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name=model_name,
-    max_seq_length=2048,
-    dtype=torch.float16,
-    load_in_4bit=True
-)
+# Load model directly
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Enable padding token if missing
 tokenizer.pad_token = tokenizer.eos_token
 
 # Set up Qdrant vector store
-qdrant_client = QdrantClient(url="https://your-qdrant-instance.com")
+qdrant_client = QdrantClient(url=QDRANT_URL, api_key = QDRANT_API_KEY)
 vector_size = 768
 embedding = HuggingFaceEmbeddings(model_name="Omartificial-Intelligence-Space/GATE-AraBert-v1")
 
@@ -164,6 +167,22 @@ iface = gr.Interface(
     theme="compact"
 )
 
+# demo = gr.ChatInterface(
+#     respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are a Medical Chatbot.", label="System message"),
+#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
+
 # Launch Gradio interface
 if __name__ == "__main__":
     iface.launch()