5 KiB
5 KiB
Lesson 03 | data types
- Links
- Notes
- set field
- 3 AI workflows
- Workflow #1 - Rag Pipeline and Chatbot
- RAG
- process
- get Google Drive Credentials
- create OAuth credentials
- Create New Credentials
- open "open docs" at the top of the dialogue
- scroll down past "Prerequisites" and click "Create a Google Cloud account https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/?utm_source=n8n_app&utm_medium=credential_settings&utm_campaign=create_new_credentials_modalt"
- create a new account
- set folder
- create OAuth credentials
- set up pinecone
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
Create New Credentials
open "open docs" at the top of the dialogue
scroll down past "Prerequisites" and click "Create a Google Cloud account https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/?utm_source=n8n_app&utm_medium=credential_settings&utm_campaign=create_new_credentials_modalt"
create a new account
-
file:../../_share/media/img/compsci/ai/herk/build_8hr/ch03_e01a.png
-
add a new project
file:../../_share/media/img/compsci/ai/herk/build_8hr/ch03_e01b.png
-
click on new project
file:../../_share/media/img/compsci/ai/herk/build_8hr/ch03_e01c.png
- select the new project
-
go to Enabled API's and services
- go to three lines in upper left and side
- click on enables API's and Services
- in the search bar add "google drive"
- enable it
-
set up OAuth consent screen
-
lets google and n8n knkow they have permission to talk to each other
file:../../_share/media/img/compsci/ai/herk/build_8hr/ch03_e01d.png
-
click on "Get Started"
- app name
- build8h-e01-ragchat
- user support email
- this.ronny@gmail.com
- under Overview - Audience, select External (using gmail account for testing)
-
- Audence -> Test users
- Clients -> name
- build8h-e01-ragchat-web-client-1
- add OAuth Redirect URL to Authorized redirect URIs
- client ID
212317400169-i0mc8cr74o0vbds6t1ticp2kbbn1ttp1.apps.googleusercontent.com- client secret
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file:../../_share/data/compsci/ai/herk/client_secret_212317400169-i0mc8cr74o0vbds6t1ticp2kbbn1ttp1.apps.googleusercontent.com.json
set folder
- save and exit the config dialog
- go to google drive trigger, and select the folder
set up pinecone
- got to http://pinecone.io