Add LiteLLM proxy model configuration and usage instructions

basic_agent.py

@@ -56,6 +56,11 @@ class BasicAgent:
             api_key=os.getenv("GROQ_API_KEY")
         )
 
+        model = LiteLLMModel(
+            model_id="groq/deepseek-r1-distill-llama-70b",
+            api_base="http://127.0.0.1:4000"
+        )
+
         # Simplified and generic tool descriptions
         python_tool_description = (
             "Executes Python code. This is vital for calculations, data manipulation, "

info.md

@@ -0,0 +1,5 @@
+use command to run liteLLM proxy and prevent rate limit errors
+
+```
+litellm --config .\litellm_config.yaml
+```

litellm_config.yaml

@@ -0,0 +1,7 @@
+model_list:
+  - model_name: deepseek-r1-distill-llama-70b
+    litellm_params:
+      model: groq/deepseek-r1-distill-llama-70b
+      api_key: os.environ/GROQ_API_KEY
+      tpm: 5000
+      rpm: 20