framsouza

this guide may help you to setup it https://github.com/framsouza/logstash-eck-ingress-controller

if you change the namespace, you need to make sure you also adjust the namespace name/connection between kibana and fleet server, see https://github.com/framsouza/eck-ready-for-production/blob/178054576aae16a2c4a267668f91bcee113f6876/kibana.yaml#L17-L18 if you are not using the default...

hey @logan-markewich , i just gave it a try: ``` tree-sitter 0.21.3 tree-sitter-go 0.21.0 tree-sitter-languages 1.10.2 llama-index 0.10.36 llama-index-core 0.10.36 ``` ``` pipeline = IngestionPipeline( transformations=[ CodeSplitter(language="go", chunk_lines=20, chunk_lines_overlap=5), Settings.embed_model...

This is the [code](https://github.com/framsouza/github-assistant/blob/7f1506ff9fdc8ecad901bdc964a15f16871e05d8/index.py#L139-L145), I'm moving from `SentenceSpliter` to `CodeSpliter` since I'm ingesting code type of information

``` llama-index==0.11.16 load_dotenv==0.1.0 tree_sitter_languages==0.21.3 llama-index-vector-stores-elasticsearch==0.3.2 llama-index-embeddings-openai==0.2.5 llama_index.llms.ollama==0.3.3 spacy==3.8.2 IPython==8.28.0 tabulate==0.9.0 ``` The `CodeSplitter` seems to work, however, the `chunk_size` doesn't seem to be applied. ``` parsers_and_extensions = [ (SentenceSplitter(chunk_size=1000, chunk_overlap=200),...