sadaf0714

Python: Unable to quantize huggingface models while creating service using semantic kernel.

7

I want to use 4-bit quantized mistral model in huggingface with semantic kernel so that I can run it on google colab free tier. But I am not able to...

Error: ValueError: Some selectors do not exist in the app or record.

10

I would like to address an issue I am encountering while fetching context relevance and groundedness feedback metrics using TruLens. I am evaluating huggingface's "meta-llama/Llama-2-7b-chat-hf" (4 bit quantized version) model...

Getting RecursionError: maximum recursion depth exceeded while calling a Python object while creating tru_recorder.

17

from trulens_eval import Feedback, LiteLLM, TruLlama from trulens_eval.feedback import Groundedness from trulens_eval.feedback.provider.hugs import Huggingface import numpy as np os.environ["HUGGINGFACE_API_KEY"] = "MY_HUGGINGFACE_API_KEY" LiteLLM.set_verbose = True provider = LiteLLM(model_engine="huggingface/mistralai/Mistral-7B-Instruct-v0.1") f_qa_relevance = Feedback(...

Unable to create vector and full text index to query my database.

3

I want to query my neo4j database's data, it has 132,000 nodes and each node have different properties. I want to create a vector index and full text index in...

[BUG]Groundedness with answerability metric not generating

4

**Bug Description** I have created a trulens application , in which i am fetching some of my RAG agent conversation history from dynamodb. It includes user query, answer and context(list...