updated new version deepseek-r1

Dockerfile

@@ -21,4 +21,4 @@ COPY . .
 EXPOSE 11434 8501
 
 # Start both Ollama and Streamlit
-CMD ["bash", "-c", "ollama serve & sleep 5 && streamlit run app.py --server.port 8501 --server.enableCORS false --server.enableXsrfProtection false"]
+# CMD ["bash", "-c", "ollama serve & sleep 5 && streamlit run app.py --server.port 8501 --server.enableCORS false --server.enableXsrfProtection false"]

README.md

@@ -3,10 +3,11 @@ title: LLM Based Custom Pdf Chatbot
 emoji: 🌖
 colorFrom: indigo
 colorTo: red
-sdk: docker
+sdk: streamlit
+sdk_version: 1.42.0
 app_file: app.py
 pinned: false
-license: apache-2.0
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

services/llm.py

@@ -23,7 +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",
+        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
@@ -71,7 +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",
+        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