updated new version deepseek-r1

services/llm.py

@@ -23,6 +23,7 @@ def initialize_qa_chain(filepath, model_name, temperature, top_p, max_tokens):
     # Configure the LLM with additional parameters
     llm = OllamaLLM(
         model=model_name,
+        base_url="https://deepak7376-ollama-server.hf.space",
         temperature=temperature,   # Controls randomness (0 = deterministic, 1 = max randomness)
         max_tokens=max_tokens,   # Limit the number of tokens in the output
         top_p=top_p          # Nucleus sampling for controlling diversity
@@ -70,6 +71,7 @@ def initialize_chain(model_name, temperature, top_p, max_tokens):
     # Configure the LLM with additional parameters
     llm = OllamaLLM(
         model=model_name,
+        base_url="https://deepak7376-ollama-server.hf.space",
         temperature=temperature,   # Controls randomness (0 = deterministic, 1 = max randomness)
         max_tokens=max_tokens,   # Limit the number of tokens in the output
         top_p=top_p          # Nucleus sampling for controlling diversity