Hey there! One quick question if i have

I think youd need to explicitly define a tool that chains together two tools

Thanks Logan! So there’s no specific way to let an agent decide which tool to launch based on another’s output?

Well, it already does that out of the box, but beyond that its just more prompt engineering. It's not entirely "controllable"

Exactly, the controllable part is the thing. I would like to avoid defining a specific tool execution order but also allowing the agent to decide which tool executing based on available data objects (output from other tools)

Perhaps ContextRetrieverOpenAIAgent could be of help in that sense, need to investigate deeply

Is agent’s tool selection only performed through it’s provided context right? What about allowing it to decide right tool using a vector db for instance? It could be an amazing feature

Vector similarity probably is far less reliable than letting the LLM decide. You'd need to have both a rich representation of the tool and a meaningful query to select

Thinking the same! So, in you opinion, what about a ContextRetrievereAgent who is able to know which tools are available for the currently obtained output objects?

I mean, a db where we can store tools description, tools input arguments (objs) and output (objs)

Then somehow query it through context retriever and adding these elements to the prompt itself?

We’re currently tryina implement a new agent module, any suggestion on that end?