How I Built Bill, the AI-Powered Chatbot That Reads Our Docs for Fun , by Todd Kerpelman at Plaid
0 likes40 views
The document discusses the development of a robotic assistant named Bill, designed to facilitate user interactions with the Plaid API for financial solutions. It outlines the technical approach including content processing, vector databases, and the integration of large language models for generating accurate responses to user queries. Additionally, it highlights considerations for improving documentation and user support through advanced data handling and technology adaptation.
![How can we make it smarter?
Can we change the way we read code?
app.post("/server/create_new_user", async (req, res, next) => {
try {
const username = escape(req.body.username);
const email = escape(req.body.email);
const userId = uuidv4();
const result = await db.run(
`INSERT INTO users(id, username, email) VALUES("${userId}", "${username}", "${email}")`
);
console.log(`User creation result is ${JSON.stringify(result)}`);
if (result["lastID"] != null) {
res.cookie("signedInUser", userId, {
maxAge: 900000,
httpOnly: true,
sameSite: "none",
secure: "false",
});
}
res.json(result);
} catch (error) {
next(error);
}
});
This code is part of a server-side application written in Node.js that interacts with
the Plaid API. It defines three functions: `getLoggedInUserId`, `getUserObject`,
and an anonymous function that handles POST requests to the "/server/
create_new_user" endpoint.
The `getLoggedInUserId` function takes a request object as an argument and
returns the value of the "signedInUser" cookie. This function is used to identify
the user who is currently logged in based on the cookies sent with the HTTP
request.
The `getUserObject` function is an asynchronous function that takes a user ID as
an argument. It queries a database for a user with the given ID and returns the
result. This function is used to retrieve the details of a user from the database.
The anonymous function is a route handler for the "/server/create_new_user"
endpoint. It is an asynchronous function that takes a request and response object,
and a next function for error handling.
When a POST request is made to this endpoint, the function first sanitizes the](https://image.slidesharecdn.com/toddkerpelmanbillthechatbot-nordicapis-240409065146-f4769f2d/85/How-I-Built-Bill-the-AI-Powered-Chatbot-That-Reads-Our-Docs-for-Fun-by-Todd-Kerpelman-at-Plaid-31-320.jpg)
How I Built Bill, the AI-Powered Chatbot That Reads Our Docs for Fun , by Todd Kerpelman at Plaid
- 1. ∏ What I learned making Bill The helpful robot platypus that reads our docs for fun
- 2. Plaid Account Veri fi cation & Payments Fraud & Compliance Personal Finance Insights Credit Underwriting Open Finance All your Fintech solutions on a single platform
- 4. The original hackathon project
- 5. How does it work?
- 6. Step 1: Chop up your content
- 7. Step 2: Figure out the "meaning" of each Mowing the lawn Weeding Making dinner Shoveling snow Chains on tires Sledding Skiing Pool Beach Hot weather Cold weather Fun Chore Cross- country skiing "Embeddings Model"
- 8. Step 3: Store all that in a database -0.0172341652,0.0231553614,0.0176660642,-0.0137998713,,0.0070 0442726,-0.0216646139,-0.00155431416,0.0154508408,-0.0206196 96,0.0172063019,0.00771148782,-0.00135577994,0.0161195882,-0. 1500-dimensional vector URL https://plaid.com/docs/signal/add-to-app/ Text for each institution that Plaid supports. Link makes it secure and easy for users to connect their bank accounts to Plaid. Note that these instructions cover Link on the web. For instructions on using Link within mobile apps, see the Link documentation.Using Link, we will Title Signal - Add Signal to your app | Plaid Docs
- 9. So, when a user asks a question... 👩💻 Hey, Bill, how do I get started with Plaid Transactions? Ooh! Lemme convert that question into a vector! These documents are closest to the vector you just sent me. User's question Vector Embeddings API Vector database Vector database
- 10. Now... we can ask our question Hey, large language model! Can you answer this user's question... ...with the help of these documents? Sure can! User's question Surprisingly accurate answer GPT-4
- 11. A simplified version of the prompt You are a helpful friendly chatbot that wants developers to be successful when using the Plaid API. You are given a question and you should answer it if you can. It's okay to say you don't know if you don't know the answer. Feel free to include detail when relevant, and include code snippets if appropriate. Here is some context that might prove useful in answering the user's question: ========= {all those documents} ========= The user's question is: "{question}" Please format your answer in Markdown.
- 12. My favorite analogy "Retrieval Augmented Generation" (or RAG)
- 13. Build vs Buy Reasons to build Reasons to buy Less expensive in the long run Faster time to market Fine control over everything Dedicated engineering teams Vendor lock-in Less manual maintenance More integrated experience You get to learn about LLMs
- 14. Build vs Buy I could build Twitter in a weekend!
- 16. Will this replace your docs team? Hooray! I still have a job!
- 17. ...but it can make your docs experience better Synthesizing information across different pages Better search than search Rephrasing generic docs for a speci fi c use case
- 18. Will this replace your support team? Hooray! I still have a job!
- 19. But you can make their lives easier Help! Our main account owner left the company! This call failed – can you look through your logs and tell us why? Can you enroll me in this beta feature? Something isn’t working as described in the docs. Help us locate the problem. Here's a question that's already answered in the documentation
- 20. GPT4? You guys rich or something?
- 22. What about user feedback?
- 23. Grade your own homework
- 24. Grade your own homework Here's a typical question from a user! 👩💻 Got it! User's question Typical Answer
- 25. Grade your own homework GPT-4 How did this chatbot do, based on this criteria? Let's say 85 outta 100 👩💻 Typical Answer
- 27. But mostly... 70% correct 25% "mostly correct" 5% plain ol' wrong
- 28. So... what happens if Bill makes a mistake? Fix the docs!
- 29. So... what happens if Bill makes a mistake? Maybe hard-code an answer?
- 30. How can we make it smarter? More isn't always better
- 31. How can we make it smarter? Can we change the way we read code? app.post("/server/create_new_user", async (req, res, next) => { try { const username = escape(req.body.username); const email = escape(req.body.email); const userId = uuidv4(); const result = await db.run( `INSERT INTO users(id, username, email) VALUES("${userId}", "${username}", "${email}")` ); console.log(`User creation result is ${JSON.stringify(result)}`); if (result["lastID"] != null) { res.cookie("signedInUser", userId, { maxAge: 900000, httpOnly: true, sameSite: "none", secure: "false", }); } res.json(result); } catch (error) { next(error); } }); This code is part of a server-side application written in Node.js that interacts with the Plaid API. It defines three functions: `getLoggedInUserId`, `getUserObject`, and an anonymous function that handles POST requests to the "/server/ create_new_user" endpoint. The `getLoggedInUserId` function takes a request object as an argument and returns the value of the "signedInUser" cookie. This function is used to identify the user who is currently logged in based on the cookies sent with the HTTP request. The `getUserObject` function is an asynchronous function that takes a user ID as an argument. It queries a database for a user with the given ID and returns the result. This function is used to retrieve the details of a user from the database. The anonymous function is a route handler for the "/server/create_new_user" endpoint. It is an asynchronous function that takes a request and response object, and a next function for error handling. When a POST request is made to this endpoint, the function first sanitizes the
- 32. How can we make it smarter? Can we change the way we parse reference docs?
- 33. Our normal reference docs... The way we show them to Bill...
- 34. How can we make it smarter? Probably the bigger problem... MORTGAGES ANNUAL PERCENTAGE RATES PAYMENT DUE DATES OVERDUE PAYMENTS
- 35. How can we make it smarter? Probably the bigger problem... SOME REFERENCE DOCS ABOUT A REST API
- 36. Other things to try, maybe... Change the way we break up text Try more, smaller chunks Try fewer, larger chunks Re fi ne how we import text Try different matching models What if we try "Three answers from the docs, 3 answers from the reference API?" Updated embeddings API
- 37. What's made the biggest impact? Using newer models Having good source material
- 38. Security Concerns Assume that any information you've fed to your chatbot could be seen verbatim by your customer.
- 40. Oh no! I'm out of time Go to kerp.blog for topics I didn't have time to discuss And thank you!