Add Llama 3 LLMs via Together AI

app.py

@@ -170,7 +170,7 @@ with st.sidebar:
         api_key_token = st.text_input(
             label=(
                 '3: Paste your API key/access token:\n\n'
-                '*Mandatory* for Cohere and Gemini LLMs.'
+                '*Mandatory* for Cohere, Google Gemini, and Together AI providers.'
                 ' *Optional* for HF Mistral LLMs but still encouraged.\n\n'
             ),
             type='password',

global_config.py

@@ -21,11 +21,13 @@ class GlobalConfig:
     PROVIDER_GOOGLE_GEMINI = 'gg'
     PROVIDER_HUGGING_FACE = 'hf'
     PROVIDER_OLLAMA = 'ol'
+    PROVIDER_TOGETHER_AI = 'to'
     VALID_PROVIDERS = {
         PROVIDER_COHERE,
         PROVIDER_GOOGLE_GEMINI,
         PROVIDER_HUGGING_FACE,
-        PROVIDER_OLLAMA
+        PROVIDER_OLLAMA,
+        PROVIDER_TOGETHER_AI
     }
     VALID_MODELS = {
         '[co]command-r-08-2024': {
@@ -53,12 +55,23 @@ class GlobalConfig:
             'max_new_tokens': 10240,
             'paid': False,
         },
+        '[to]meta-llama/Llama-3.3-70B-Instruct-Turbo': {
+            'description': 'detailed, slower',
+            'max_new_tokens': 4096,
+            'paid': True,
+        },
+        '[to]meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-128K': {
+            'description': 'shorter, faster',
+            'max_new_tokens': 4096,
+            'paid': True,
+        },
     }
     LLM_PROVIDER_HELP = (
         'LLM provider codes:\n\n'
         '- **[co]**: Cohere\n'
         '- **[gg]**: Google Gemini API\n'
         '- **[hf]**: Hugging Face Inference API\n'
+        '- **[to]**: Together AI\n'
     )
     DEFAULT_MODEL_INDEX = 3
     LLM_MODEL_TEMPERATURE = 0.2

helpers/llm_helper.py

@@ -84,6 +84,7 @@ def is_valid_llm_provider_model(provider: str, model: str, api_key: str) -> bool
     if provider in [
         GlobalConfig.PROVIDER_GOOGLE_GEMINI,
         GlobalConfig.PROVIDER_COHERE,
+        GlobalConfig.PROVIDER_TOGETHER_AI,
     ] and not api_key:
         return False
 
@@ -161,6 +162,19 @@ def get_langchain_llm(
             streaming=True,
         )
 
+    if provider == GlobalConfig.PROVIDER_TOGETHER_AI:
+        from langchain_together import Together
+
+        logger.debug('Getting LLM via Together AI: %s', model)
+        return Together(
+            model=model,
+            temperature=GlobalConfig.LLM_MODEL_TEMPERATURE,
+            together_api_key=api_key,
+            max_tokens=max_new_tokens,
+            top_k=40,
+            top_p=0.90,
+        )
+
     if provider == GlobalConfig.PROVIDER_OLLAMA:
         from langchain_ollama.llms import OllamaLLM
 

requirements.txt

@@ -12,6 +12,7 @@ langchain-core~=0.3.0
 langchain-community==0.3.0
 langchain-google-genai==2.0.6
 langchain-cohere==0.3.3
+langchain-together==0.3.0
 langchain-ollama==0.2.1
 streamlit~=1.38.0