learning about rag workflow

build n8n ai agents - 8 hr course/_subsections/lesson-03.org

@@ -8,6 +8,8 @@
 - [[../toc.org][TOC | Build n8n ai agents 8 hr course]]
 - [[https://www.youtube.com/watch?v=Ey18PDiaAYI][Course Video]]
 
+Curr: https://youtu.be/Ey18PDiaAYI?si=OFqJ3CX3m2AHLWdV&t=3270
+
 *** timestamps
 :PROPERTIES:
 :CUSTOM_ID: timestamp
@@ -16,5 +18,71 @@
 #+attr_html: :class playlist
 - [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=2445s][0:40:45 n8n n8n Data Types]]
 - [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=2905s][0:48:25 23 Workflow Templates FREE]]
+- [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=2949s][0:49:09 Step by Step AI Workflows]]
+- [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=3085s][0:51:25 1) Rag Pipeline and Chatbot]]
+- [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=4262s][1:11:02 2) Customer Support Workflow]]
+- [[https://www.youtube.com/watch?v=Ey18PDiaAYI&t=4926s][1:22:06 3) LinkedIn Content Creator Workflow]]
 
 * Notes
+** set field
+- can also name the fields and data type for each field
+
+*** data types
+| data type | symbol | example             |
+|-----------+--------+---------------------|
+| String    | A      | "blah"              |
+| Number    | #      | 50                  |
+| Boolean   | ✓      | true                |
+| Array     | ☰     | [1, "one", "three"] |
+| Object    | 3d box | {"blah": 33}        |
+
+** 3 AI workflows
+*** 1. RAG pipeline & chatbot
+**** tools
+- pinecone :: vector database
+- google drive :: data storage
+- google docs ::
+- open router :: lets us connect to ai models like openai's or anthropics
+
+*** 2. Customer support
+**** purpose
+- build off prev workflow with pinecone db
+- respond to customer support related emails
+
+**** tools
+- pinecone
+- gmail
+- n8n agent
+- open router
+
+*** 3. LinkedIn Content Creation
+**** tools
+- tavily :: search the web
+- google sheets :: store content ideas, and write content ideas to it
+
+** Workflow #1 - Rag Pipeline and Chatbot
+*** RAG
+- stands for :: retrieval, augmented, generation
+- looks inside database for the answer
+
+**** Vector Database
+- multidimensional graph of points
+- vector is placed based on meaning of vector
+  - ie, wolf and dog will be close
+  - banana, apple will be close
+
+**** how it works
+- we have a document
+- break it into chunks
+- run it through an 'embeddings model'
+  - this puts the chunks into a vector model
+
+**** Query
+- run the query through the embeddings model
+- see where it lands in vectors, grabs back the nearest 4 or 5 vectors and returns it to us
+
+*** process
+- our trigger is any changes in folder on google drive
+
+**** get Google Drive Credentials
+***** create OAuth credentials

build n8n ai agents - 8 hr course/toc.org

@@ -10,7 +10,7 @@
 - [[https://www.youtube.com/@nateherk][Nate Herk Channel]]
 - [[https://www.youtube.com/@nateherk/playlists][Playlists]]
 
-Curr: https://youtu.be/Ey18PDiaAYI?si=EYpBQh_b-Xf9FB6i&t=2445
+Curr: https://youtu.be/Ey18PDiaAYI?si=OFqJ3CX3m2AHLWdV&t=3270
 
 *** playlist
 :PROPERTIES: