openai supabase ai

docs/saas/openai.md

@@ -8,20 +8,6 @@ OpenAI Docs - <https://platform.openai.com/docs>
 OpenAI API Reference - <https://platform.openai.com/docs/api-reference>  
 Plugins - <https://platform.openai.com/docs/plugins>  
 
-
-
-### Repos
-
-Llama Index - <https://gpt-index.readthedocs.io/en/latest/>  
-Llama Index - <https://github.com/jerryjliu/llama_index>
-
-LangChain - <https://python.langchain.com/en/latest/index.html>  
-LangChain repo -<https://github.com/hwchase17/langchain>
-
-
-
-
-
 ### Videos
 
 - Build Your Own Auto-GPT Apps with LangChain - <https://www.youtube.com/watch?v=NYSWn1ipbgg> / <https://github.com/daveebbelaar/langchain-experiments>
@@ -158,3 +144,13 @@ Installing packaging (23.0)
   • Installing weaviate-client (3.15.4)
 Installing the current project: chatgpt-retrieval-plugin (0.1.0)
 ```
+
+## See Also: 
+
+### Repos
+
+Llama Index - <https://gpt-index.readthedocs.io/en/latest/>  
+Llama Index - <https://github.com/jerryjliu/llama_index>
+
+LangChain - <https://python.langchain.com/en/latest/index.html>  
+LangChain repo -<https://github.com/hwchase17/langchain>

docs/saas/supabase.md

@@ -1,4 +1,25 @@
 # SupaBase
 
-- <https://supabase.com/vector>
-- <https://github.com/supabase/supabase>
+I mostly try to avoid SaaS unless they can do a much better job than I can for cheaper. I've previously used hosted Postgres databases at Heroku. I'm starting with the hosted version and experimenting with the self hosted version to see how well I can maintain it.
+
+I started with an [AI project](/ai) to import all of the markdown files from this documentation but I'm starting another test project so that I can learn how to more accurately control the vector embeddings.
+
+## Log
+
+## Dashboard 
+
+- <https://supabase.com/dashboard/>
+
+## Docs
+
+- Docs <https://supabase.com/docs>
+- Guides <https://supabase.com/docs>
+- Vector <https://supabase.com/vector>
+
+## Repos
+
+- <https://github.com/supabase/supabase>
+
+## Notes
+
+-

notes/work/projects/ai.md

@@ -1,14 +1,28 @@
-# AI Assistant
+# AI
 
 👉🏼 I've added a working demo @ [/ai](/ai)
 
-Semantic search is powerful and it's part of the reason I build and publish this Today I Learned section on my website. Semantic search is even more powerful when you add natural language processing trained on a large language model. I'm making this page for notes on building a personal AI Assistant. 
 
-### Background
+
+### About
+
+Semantic search is powerful and it's part of the reason I build and publish this Today I Learned section on my website. Semantic search is even more powerful when you add natural language processing trained on a large language model. I'm making this page for notes on building a personal AI Assistant. 
 
 I written several essays in the last couple years on using tools to organize my workflow and thinking <sub>1,2</sub>. In the last six months I've written two on Artificial Intelligence <sub>3,4</sub>. I now use several different AI assistants within my text editor for coding. The same way I've applied my code documentation to the rest of my life here, I'm starting to realize how helpful AI assistants can be. I think I'll need one to interact with my public documentation and a second for me to interact with my private information like my calendar, chats, and emails.  
 
-I've recently started learning how to create embeddings using vector databases which can be chained to existing LLMs. I've started some documentation using LangChain and OpenAi @ [/docs/saas/OpenAI](/docs/saas/OpenAI) <sub>5</sub>. Because the field is rapidly developing, I need a place to keep notes on it, so here we are. 
+I've recently started learning how to create embeddings using vector databases which can be chained to existing LLMs. I've started some documentation using LangChain and OpenAi <sub>5</sub>. Because the field is rapidly developing, I need a place to keep notes on it, so here we are. 
+
+## Docs
+
+- OpenAi [/docs/saas/openai](/docs/saas/openai)
+- SupaBase [/docs/saas/supabase](/docs/saas/supabase)
+
+## Stack
+
+- React
+- Next.js
+- Vercel
+- Supabase
 
 #### Context Injection
 
@@ -27,16 +41,6 @@ I've recently started learning how to create embeddings using vector databases w
 
 #### Fine Tuning vs. Semantic Search
 
-
-## Stack 
-
-- React
-- Next.js
-- Express
-- Vercel
-- Supabase
-
-
 ## ToDo
 
 - fix all relative links so that result links work
@@ -48,13 +52,13 @@ I've recently started learning how to create embeddings using vector databases w
   - return to exporting my post into markdown or migrate
 - iterative testing of various prompts
 
-### Docs 
+## Docs 
 
 - <https://supabase.com/docs/guides/api>
 - <https://gpt-index.readthedocs.io/en/latest/>
 
 
-### Repos 
+## Repos 
 
 - PGVector <https://github.com/pgvector/pgvector>
 - SupaBase <https://github.com/supabase/supabase>
@@ -69,7 +73,7 @@ I've recently started learning how to create embeddings using vector databases w
 - Llama Index GPT Retrieval Plugin - <https://llamahub.ai/l/chatgpt_plugin>
 
 
-### Resources
+## Resources
 
 - ChatGPT for Supabase Docs - <https://supabase.com/blog/chatgpt-supabase-docs>
 - How I Built Supabase’s OpenAI Doc Search - <https://www.youtube.com/watch?v=Yhtjd7yGGGA>
@@ -78,15 +82,13 @@ I've recently started learning how to create embeddings using vector databases w
 - Mendable switches from Pinecone to Supabase for vector embeddings - <https://supabase.com/customers/mendableai>
 - Supabase Clippy: ChatGPT for Supabase Docs - <https://supabase.com/blog/chatgpt-supabase-docs>
 
-### Commercial Products
+## Commercial Products
 
 - Mendable - <https://www.mendable.ai>
 - MarkPrompt - <https://markprompt.com>
 
-
-
 ---
-### References
+## References
 
 1. _Slow Thinking_ - <https://davidawindham.com/slow-thinking/>
 2. _A Second Brain_ - <https://davidawindham.com/a-second-brain/>