set the embedding model in an environment variable

iterations/v2-agentic-workflow/.env.example

@@ -30,4 +30,8 @@ REASONER_MODEL=
 
 # The LLM you want to use for the primary agent/coder.
 # Example: gpt-4o-mini
-PRIMARY_MODEL=
+PRIMARY_MODEL=
+
+# Embedding model you want to use (nomic-embed-text:latest, text-embedding-3-small)
+# Example: nomic-embed-text:latest
+EMBEDDING_MODEL=

iterations/v2-agentic-workflow/crawl_pydantic_ai_docs.py

@@ -22,6 +22,8 @@ base_url = os.getenv('BASE_URL', 'https://api.openai.com/v1')
 api_key = os.getenv('LLM_API_KEY', 'no-llm-api-key-provided')
 is_ollama = "localhost" in base_url.lower()
 
+embedding_model = os.getenv('EMBEDDING_MODEL', 'text-embedding-3-small')
+
 openai_client=None
 
 if is_ollama:
@@ -115,7 +117,7 @@ async def get_embedding(text: str) -> List[float]:
     """Get embedding vector from OpenAI."""
     try:
         response = await openai_client.embeddings.create(
-            model= "nomic-embed-text:latest" if is_ollama else "text-embedding-3-small",
+            model= embedding_model,
             input=text
         )
         return response.data[0].embedding

iterations/v2-agentic-workflow/ollama_site_pages.sql

@@ -10,7 +10,7 @@ create table site_pages (
     summary varchar not null,
     content text not null,  -- Added content column
     metadata jsonb not null default '{}'::jsonb,  -- Added metadata column
-    embedding vector(768),  -- OpenAI embeddings are 1536 dimensions
+    embedding vector(768),  -- Ollama nomic-embed-text embeddings are 768 dimensions
     created_at timestamp with time zone default timezone('utc'::text, now()) not null,
     
     -- Add a unique constraint to prevent duplicate chunks for the same URL

iterations/v2-agentic-workflow/pydantic_ai_coder.py

@@ -19,6 +19,7 @@ llm = os.getenv('PRIMARY_MODEL', 'gpt-4o-mini')
 base_url = os.getenv('BASE_URL', 'https://api.openai.com/v1')
 api_key = os.getenv('LLM_API_KEY', 'no-llm-api-key-provided')
 model = OpenAIModel(llm, base_url=base_url, api_key=api_key)
+embedding_model = os.getenv('EMBEDDING_MODEL', 'text-embedding-3-small')
 
 logfire.configure(send_to_logfire='if-token-present')
 
@@ -90,7 +91,7 @@ async def get_embedding(text: str, openai_client: AsyncOpenAI) -> List[float]:
     """Get embedding vector from OpenAI."""
     try:
         response = await openai_client.embeddings.create(
-            model= "nomic-embed-text:latest" if is_ollama else "text-embedding-3-small",
+            model= embedding_model,
             input=text
         )
         return response.data[0].embedding