Changed the api and gave permissions to make directory same local model

Dockerfile

@@ -31,6 +31,10 @@ ENV HOME=/app
 ENV HF_HOME /app/.cache/huggingface
 RUN mkdir -p ${HF_HOME} && chown -R 1000:1000 ${HF_HOME}
 
+# Create and set permissions for the GPT4All cache directory
+RUN mkdir -p /app/.cache/gpt4all && \
+    chown -R 1000:1000 /app/.cache/gpt4all
+
 # Tell the container to listen on the port provided by Cloud Run
 EXPOSE 7860
 

backend/app.py

@@ -303,7 +303,7 @@ def ask_question_endpoint():
             try:
                 chat_completion = api_llm.chat.completions.create(
                     messages=[{"role": "user", "content": prompt}],
-                    model="llama3-8b-8192",
+                    model="llama3-70b-8192", # Use a current, supported model
                     temperature=0.5, max_tokens=250
                 )
                 response = chat_completion.choices[0].message.content