Update helper_functions_api.py

helper_functions_api.py

@@ -82,22 +82,45 @@ def limit_tokens(input_string, token_limit=7500):
     """
     return encoding.decode(encoding.encode(input_string)[:token_limit])
 
-def together_response(message, model = "meta-llama/Llama-3-8b-chat-hf", SysPrompt = SysPromptDefault, temperature=0.2, frequency_penalty =0.1, max_tokens= 2000):
-    client = OpenAI(
+together_client = OpenAI(
         api_key=TOGETHER_API_KEY, 
         base_url="https://together.hconeai.com/v1", 
         default_headers={ "Helicone-Auth": f"Bearer {HELICON_API_KEY}"})
+
+groq_client = OpenAI(
+        api_key=GROQ_API_KEY, 
+        base_url="https://groq.hconeai.com/openai/v1", 
+        default_headers={ "Helicone-Auth": f"Bearer {HELICON_API_KEY}"})
+
+# Groq model names
+llm_default_small = "llama3-8b-8192"
+llm_default_medium = "llama3-70b-8192"
+
+# Together Model names (fallback)
+llm_fallback_small = "meta-llama/Llama-3-8b-chat-hf"
+llm_fallback_medium = "meta-llama/Llama-3-70b-chat-hf"
+
+### ------END OF LLM CONFIG-------- ###
+
+def together_response(message, model = llm_default_small, SysPrompt = SysPromptDefault, temperature=0.2, frequency_penalty =0.1, max_tokens= 2000):
     
     messages=[{"role": "system", "content": SysPrompt},{"role": "user", "content": message}]
+    params = {
+      "model": model,
+      "messages": messages,
+      "temperature": temperature,
+      "frequency_penalty": frequency_penalty,
+      "max_tokens": max_tokens
+    }
+    try:
+      response = groq_client.chat.completions.create(**params)
+      return response.choices[0].message.content
     
-    response = client.chat.completions.create(
-        model=model,
-        messages=messages,
-        temperature=temperature,
-        frequency_penalty = frequency_penalty
-        )
-    return response.choices[0].message.content
-
+    except Exception as e:
+      print(f"Error calling GROQ API: {e}")
+      params["model"] = llm_fallback_small if model == llm_default_small else llm_fallback_medium 
+      response = together_client.chat.completions.create(**params)
+      return response.choices[0].message.content
 
 def json_from_text(text):
     """