Vincent Giraud

Lenses error with zeebe source connector

1

Hello, We are using Lenses.io and while zeebe sink connector will install without issue, zeebe source creation is getting an error (even when setting all properties): "Cannot extract connector information...

Create a Windows version of the patch.bat post renderer script for Open Shift

1

**Describe the use case:** As a DevOps I want to be able to Helm install from a Windows computer on Open Shift We are required to adapt (hence debug) the...

Auth token renewal

1

**Is your feature request related to a problem? Please describe.** Once the oauth token expired, an "unauthenticated" grpc exception will be raised: "Failed to parse bearer token, see cause for...

Querying completed workflow instances by datetime range

2

Support querying completed workflow instances by datetime range. e.g. For processes and variables on a particular day. ``` { processInstances (stateIn: [COMPLETED], minStartTime: "2021-11-02T00:00:00.000Z", maxEndTime: "2021-11-02T23:59:59.999Z") { nodes { state...

LLM and Prompty tools only support jinja2 files which forbids a low code user from using prompty file e2e: from experimentation to depoyment within a DAG flow: ...

Fix for issue 69 when using structured output for AOAI

4

Fix for issue 69 when using structured output for AOAI: 'You tried to pass a BaseModel class to chat.completions.create(); You must use beta.chat.completions.parse() instead. Basically an upgrade of AOAI client...

Support for structured outputs or function calling

8

Is there any plan to support [structured output](https://platform.openai.com/docs/guides/structured-outputs/introduction?context=ex1) as response format or [function calling](https://platform.openai.com/docs/guides/function-calling) in Prompty?  

Built-in guidance for constrained generation and more predictable outputs

1

[Guidance](https://github.com/guidance-ai/guidance) allows users to constrain generation (e.g. with regex and CFGs) as well as to interleave control (conditionals, loops, tool use) and generation for more predictable outputs. It's been recently...

Built-in prompt compression

2

Optimization being part of prompt design, it'd be great to integrate a tool like [LLMLingua](https://github.com/microsoft/LLMLingua) in the VSC extension. The prompty file could have a `compression` section: ``` compression: rate:...

#### Fixes #419 #### What does this implement/fix? Explain your changes. - Added missing libraries to `pyproject.toml` - Added gpt-4o in the model list - Added env vars for Azure...