Rima

Hello @PablocFonseca , fantastic library! I just have one question, how can we specify height to be adjustable to the number of rows in the table? for example: I have...

Hello @ghilesmeddour , thank you I just figured that out as well :) ! Although I think the best values are: MIN_HEIGHT = 27 MAX_HEIGHT = 800 ROW_HEIGHT = 35

Hello @PablocFonseca , is their a way to keep wrapText = True and use Height ? It seems that if we remove autoHeight = True, the wrapText will not work....

I just found a simply temporary solution and it worked for me! In your module, where you are loading the mlflow model, put the following code: ``` import transformers transformers.LSGDistilBertForSequenceClassification...

I created the **OpenAIChatGenerator** (very much inspired from what @TuanaCelik has done) ``` class CustomOpenAIGenerator(OpenAIChatGenerator): """Same as OpenAIGenerator but with response_format""" def __init__(self, **kwargs): super().__init__(**kwargs) @component.output_types(replies=List[str], meta=List[Dict[str, Any]], structured_reply=BaseModel) def...

I can work on that as I already implemented it locally

@LastRemote @vblagoje So currently the OpenAIChatGenerator with stream=True is giving in usage `completion_start_time` anytime to have directly the number of seconds to have the TTFT? Another question, is it supposed...

> Yes, you need to use main I believe @rhajou - TTFT across many chat generators should be in the next release (less than a month away). TTFT works with...

Hello came here with the same problem but with a different implementation. I am facing issues parallelizing retrieving data from the Pgvector store using PgvectorEmbeddingRetriever, as I need to retrieve...

@phiweger I will drop my code here for more clarification: ``` import threading import openai import time import os from src.helpers.formatter import create_conn_str from haystack_integrations.document_stores.pgvector import \ PgvectorDocumentStore from haystack_integrations.components.retrievers.pgvector...