Titus Lim

What config did you use to have the model return the activations?

1

Hello, I'm trying to understand why your model is returning 3 activations along with the outputs when running inferences. line 27 of main.py: activation1_s, activation2_s, activation3_s, output_s = snet(img) Was...

[Feature Request]: Add function calling tool for LLMs on AWS Bedrock

1

### Feature Description I am trying to instantiate an agentworker from tools with my AWS Bedrock LLM. However I received the error ```ValueError: Model name mistral.mixtral-8x7b-instruct-v0:1 does not support function...

**Is your feature request related to a problem? Please describe.** The Vanna AI library is great. I just can't help noticing that the tool is best suited for easier questions...

### Feature Description DSPy's update to 2.4.12 causes the LlamaIndex integration to break. The biggest change in 2.4.12 is that ChainOfThought is now taken to be a module. The DSPyComponent...

Add human-in-the-loop capabilities

2

**Is your feature request related to a problem? Please describe.** There are more agentic applications that have human-in-the-loop as a feature (implemented in langgraph, llamaindex, and autogen). There is currently...

Add support for python 3.12

3

## 🚀 Feature Request Giskard currently supports up till python 3.11. This request is to extend support for python 3.12. ## 🔈 Motivation Python 3.12 has had a number of...

Include a pandas dataframe element

6

**Is your feature request related to a problem? Please describe.** Chainlit offers many elements that can be tagged to a message. I would like to suggest loading a pandas dataframe...

dspyComponent module only allows for a dspy.Predict module as input

4

I was following the llamaindex cookbook and reached an error for the code ``` dspy_component = DSPyComponent(dspy.ChainOfThought(GenerateAnswer)) ``` The error trace showed that there was a pydantic validation error for...