Changed provider/model delimiter to ':'

README.md

@@ -72,7 +72,7 @@ python search_agent.py [OPTIONS] SEARCH_QUERY
 - `-c`, `--copywrite`: First produce a draft, review it, and rewrite for a final text.
 - `-d DOMAIN`, `--domain=DOMAIN`: Limit search to a specific domain.
 - `-t TEMP`, `--temperature=TEMP`: Set the temperature of the LLM [default: 0.0].
-- `-m MODEL`, `--model=MODEL`: Use a specific model [default: openai/gpt-4o-mini].
+- `-m MODEL`, `--model=MODEL`: Use a specific model [default: openai:gpt-4o-mini].
 - `-e MODEL`, `--embedding_model=MODEL`: Use a specific embedding model [default: same provider as model].
 - `-n NUM`, `--max_pages=NUM`: Max number of pages to retrieve [default: 10].
 - `-x NUM`, `--max_extracts=NUM`: Max number of page extracts to consider [default: 7].
@@ -82,11 +82,15 @@ python search_agent.py [OPTIONS] SEARCH_QUERY
 ### Examples
 
 ```bash
-python search_agent.py -m openai/gpt-4o-mini "Write a linked post about the current state of M&A for startups. Write in the style of Russ from Silicon Valley TV show."
+python search_agent.py -m openai:gpt-4o-mini "Write a linked post about the current state of M&A for startups. Write in the style of Russ from Silicon Valley TV show."
 ```
 
 ```bash
- python search_agent.py -m openai -e ollama -t 0.7 -n 20 -x 15  "Write a linked post about the state of M&A for startups in 2024. Write in the style of Russ from TV show Silicon Valley" -s   
+ python search_agent.py -m groq:llama-3.1-70b-versatile -e ollama:nomic-embed-text:latest -t 0.7 -n 20 -x 15  "Write a linked post about the state of M&A for startups in 2024. Write in the style of Russ from TV show Silicon Valley" -s   
+```
+
+```bash
+ python search_agent.py -m groq -e openai "Write an engaging long linked post about the state of M&A for startups in 2024"
 ```
 
 ## License

models.py

@@ -28,10 +28,14 @@ from langchain_community.chat_models import ChatPerplexity
 from langchain_together import ChatTogether
 from langchain_together.embeddings import TogetherEmbeddings
 
-
+def split_provider_model(provider_model):
+    parts = provider_model.split(':', 1)
+    provider = parts[0]
+    model = parts[1] if len(parts) > 1 else None
+    return provider, model
 
 def get_model(provider_model, temperature=0.0):
-    provider, model = (provider_model.rstrip('/').split('/') + [None])[:2]
+    provider, model = split_provider_model(provider_model)
     match provider:
         case 'bedrock':
             if model is None:
@@ -76,8 +80,8 @@ def get_model(provider_model, temperature=0.0):
     return chat_llm
 
 
-def get_embedding_model(provider_embedding_model):
-    provider, model = (provider_embedding_model.rstrip('/').split('/') + [None])[:2]
+def get_embedding_model(provider_model):
+    provider, model = split_provider_model(provider_model)
     match provider:
         case 'bedrock':
             if model is None:
@@ -224,7 +228,7 @@ class TestGetModel(unittest.TestCase):
     @patch('models.ChatGroq')
     def test_groq_model(self, mock_groq):
         result = get_model('groq')
-        mock_groq.assert_called_once_with(model_name='llama2-70b-4096', temperature=0.0)
+        mock_groq.assert_called_once_with(model_name='llama-3.1-8b-instant', temperature=0.0)
         self.assertEqual(result, mock_groq.return_value)
 
     @patch('models.ChatOllama')

search_agent.py

@@ -12,6 +12,7 @@ Usage:
         [--max_extracts=num]
         [--use_selenium]
         [--output=text]
+        [--verbose]
         SEARCH_QUERY
     search_agent.py --version
 
@@ -27,6 +28,7 @@ Options:
     -x num --max_extracts=num           Max number of page extract to consider [default: 7]
     -s --use_selenium                   Use selenium to fetch content from the web [default: False]
     -o text --output=text               Output format (choices: text, markdown) [default: markdown]
+    -v --verbose                        Print verbose output [default: False]
 
 """
 
@@ -80,6 +82,7 @@ if os.getenv("LANGCHAIN_API_KEY"):
     )
 @traceable(run_type="tool", name="search_agent")
 def main(arguments):
+    verbose = arguments["--verbose"]
     copywrite_mode = arguments["--copywrite"]
     model = arguments["--model"]
     embedding_model = arguments["--embedding_model"]
@@ -98,6 +101,10 @@ def main(arguments):
     else:
         embedding_model = md.get_embedding_model(embedding_model)
 
+    if verbose:
+        console.log(f"Using model: {chat.model_name}")
+        console.log(f"Using embedding model: { embedding_model.model}")
+
     with console.status(f"[bold green]Optimizing query for search: {query}"):
         optimize_search_query = wr.optimize_search_query(chat, query)
         if len(optimize_search_query) < 3: