Jason Liu

Systems.

3

A bit hand wavy but the guys working on the datastore and systems should talk together and think of smart ways to automate the systems involved and to connect all...

we will also need a way for admins to access and interact with the data we provide.

Now that the MongoDB is set up we'll need some class that can obtain everything before transforming it for our training algorithms

A lot of discussion needs to be had about how we want to do all the procesing. Will we be using a messaging broker? What technologies will ne required? Some...

We will need to have some automated ways to train and test our algorithm and serlize them into our data store. We will need to think of relevant features and...

I'm going to slowly try to refactor this thing. I would love some help. Here are some core components of the Mark Sweep project, each will have its own main...

# Problem I noticed that in order to change the prefix of the prompt in the `zero-shot-react-description` agent we had to dig around to subset strings deep into the agent's...

Exploiting llm-math (and likely PAL) and suggesting and alternative

2

#Overview llm math and PAL both use `exec()` and `eval()` which is dangerous, while PAL is more complex and might have to stay that way, llm-math could be made safer...

Add QuerySQLWithSubqueryDataBaseTool and support for WITH clause

1

This is based on converations with @fpingham on discord. I add two additional tips in the `QuerySQLWithSubqueryDataBaseTool` that adds two new prompts that aim to mirror CoT like behavior for...

Validated Schema

6

**Is your feature request related to a problem? Please describe.** I'm the maintainer of [Instructor](https://jxnl.github.io/instructor/) which uses pydantic (python's validation) library to improve the sdk usaibility. If I wanted to...