Updating root of repo for v3 release branch

.env.example

@@ -4,16 +4,17 @@
 # OpenRouter: https://openrouter.ai/api/v1
 BASE_URL=
 
-# Get your Open AI API Key by following these instructions -
-# https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key
-# Even if using OpenRouter/Ollama, you still need to set this for the embedding model.
-# Future versions of Archon will be more flexible with this.
-OPENAI_API_KEY=
-
 # For OpenAI: https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key
 # For OpenRouter: https://openrouter.ai/keys
+# For Ollama, no need to set this unless you specifically configured an API key
 LLM_API_KEY=
 
+# Get your Open AI API Key by following these instructions -
+# https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key
+# Even if using OpenRouter, you still need to set this for the embedding model.
+# No need to set this if using Ollama.
+OPENAI_API_KEY=
+
 # For the Supabase version (sample_supabase_agent.py), set your Supabase URL and Service Key.
 # Get your SUPABASE_URL from the API section of your Supabase project settings -
 # https://supabase.com/dashboard/project/<your project ID>/settings/api
@@ -32,4 +33,9 @@ REASONER_MODEL=
 # The LLM you want to use for the primary agent/coder.
 # Example: gpt-4o-mini
 # Example: qwen2.5:14b-instruct-8k
-PRIMARY_MODEL=
+PRIMARY_MODEL=
+
+# Embedding model you want to use
+# Example for Ollama: nomic-embed-text
+# Example for OpenAI: text-embedding-3-small
+EMBEDDING_MODEL=

README.md

@@ -67,7 +67,6 @@ Archon demonstrates three key principles in modern AI development:
 - LangSmith
 - Other frameworks besides Pydantic AI
 - Other vector databases besides Supabase
-- Alternative embedding models besides OpenAI
 
 ## Getting Started with V3 (current version)
 
@@ -152,6 +151,7 @@ This will:
 1. Set up the database:
    - Execute `utils/site_pages.sql` in your Supabase SQL Editor
    - This creates tables and enables vector similarity search
+   - See the Database Setup section for more details
 
 2. Crawl documentation:
 ```bash
@@ -202,8 +202,12 @@ The interface will be available at `http://localhost:8501`
 - `utils/`: Utility functions and database setup
   - `utils.py`: Shared utility functions
   - `site_pages.sql`: Database setup commands
+  - `site_pages_ollama.sql`: Database setup commands with vector dimensions updated for nomic-embed-text  
+
+### Database Setup
+
+The Supabase database uses the following schema:
 
-### Database Schema
 ```sql
 CREATE TABLE site_pages (
     id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
@@ -213,10 +217,19 @@ CREATE TABLE site_pages (
     summary TEXT,
     content TEXT,
     metadata JSONB,
-    embedding VECTOR(1536)
+    embedding VECTOR(1536) -- Adjust dimensions as necessary (i.e. 768 for nomic-embed-text)
 );
 ```
 
+Execute the SQL commands in `utils/site_pages.sql` to:
+1. Create the necessary tables
+2. Enable vector similarity search
+3. Set up Row Level Security policies
+
+In Supabase, do this by going to the "SQL Editor" tab and pasting in the SQL into the editor there. Then click "Run".
+
+If using Ollama with the nomic-embed-text embedding model or another with 786 dimensions, either update site_pages.sql so that the dimensions are 768 instead of 1536 or use `utils/ollama_site_pages.sql`
+
 ## Contributing
 
 We welcome contributions! Whether you're fixing bugs, adding features, or improving documentation, please feel free to submit a Pull Request.

archon/archon_graph.py

@@ -48,7 +48,13 @@ end_conversation_agent = Agent(
     system_prompt='Your job is to end a conversation for creating an AI agent by giving instructions for how to execute the agent and they saying a nice goodbye to the user.',  
 )
 
-openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+openai_client=None
+
+if is_ollama:
+    openai_client = AsyncOpenAI(base_url=base_url,api_key=api_key)
+else:
+    openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
 supabase: Client = Client(
     os.getenv("SUPABASE_URL"),
     os.getenv("SUPABASE_SERVICE_KEY")

archon/crawl_pydantic_ai_docs.py

@@ -17,7 +17,20 @@ from supabase import create_client, Client
 load_dotenv()
 
 # Initialize OpenAI and Supabase clients
-openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+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:
+    openai_client = AsyncOpenAI(base_url=base_url,api_key=api_key)
+else:
+    openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
 supabase: Client = create_client(
     os.getenv("SUPABASE_URL"),
     os.getenv("SUPABASE_SERVICE_KEY")
@@ -88,7 +101,7 @@ async def get_title_and_summary(chunk: str, url: str) -> Dict[str, str]:
     
     try:
         response = await openai_client.chat.completions.create(
-            model=os.getenv("LLM_MODEL", "gpt-4o-mini"),
+            model=os.getenv("PRIMARY_MODEL", "gpt-4o-mini"),
             messages=[
                 {"role": "system", "content": system_prompt},
                 {"role": "user", "content": f"URL: {url}\n\nContent:\n{chunk[:1000]}..."}  # Send first 1000 chars for context
@@ -104,7 +117,7 @@ async def get_embedding(text: str) -> List[float]:
     """Get embedding vector from OpenAI."""
     try:
         response = await openai_client.embeddings.create(
-            model="text-embedding-3-small",
+            model= embedding_model,
             input=text
         )
         return response.data[0].embedding
@@ -231,7 +244,20 @@ def get_pydantic_ai_docs_urls() -> List[str]:
         print(f"Error fetching sitemap: {e}")
         return []
 
+async def clear_existing_records():
+    """Clear all existing records with source='pydantic_ai_docs' from the site_pages table."""
+    try:
+        result = supabase.table("site_pages").delete().eq("metadata->>source", "pydantic_ai_docs").execute()
+        print("Cleared existing pydantic_ai_docs records from site_pages")
+        return result
+    except Exception as e:
+        print(f"Error clearing existing records: {e}")
+        return None
+
 async def main():
+    # Clear existing records first
+    await clear_existing_records()
+    
     # Get URLs from Pydantic AI docs
     urls = get_pydantic_ai_docs_urls()
     if not urls:

archon/pydantic_ai_coder.py

@@ -19,8 +19,11 @@ 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')
+logfire.configure(send_to_logfire='if-token-present')
+
+is_ollama = "localhost" in base_url.lower()
 
 @dataclass
 class PydanticAIDeps:
@@ -88,7 +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="text-embedding-3-small",
+            model=embedding_model,
             input=text
         )
         return response.data[0].embedding

iterations/v3-mcp-support/README.md

@@ -187,6 +187,7 @@ CREATE TABLE site_pages (
 - `utils/`: Utility functions and database setup
   - `utils.py`: Shared utility functions
   - `site_pages.sql`: Database setup commands
+  - `site_pages_ollama.sql`: Database setup commands with vector dimensions updated for nomic-embed-text
 
 ### Runtime
 - `workbench/`: Runtime files and logs

streamlit_ui.py

@@ -33,7 +33,17 @@ from archon.archon_graph import agentic_flow
 from dotenv import load_dotenv
 load_dotenv()
 
-openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+openai_client=None
+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()
+
+if is_ollama:
+    openai_client = AsyncOpenAI(base_url=base_url,api_key=api_key)
+else:
+    openai_client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
 supabase: Client = Client(
     os.getenv("SUPABASE_URL"),
     os.getenv("SUPABASE_SERVICE_KEY")