💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python agentsaiai-agentsembeddingsinformation-retrievallanguage-modellarge-language-modelsllmnlppythonragretrieval-augmented-generationsearchsearch-enginesemantic-searchsentence-embeddingstransformerstxtaivector-databasevector-search
Update documentation, closes #646
davidmezzettic09907f5fa5c
diff --git a/docs/faq.md b/docs/faq.mdindex c18a4d67..567510ae 100644--- a/docs/faq.md+++ b/docs/faq.md@@ -112,3 +112,17 @@ __Issue____Solution__Restart the kernel. See issue [#409](https://github.com/neuml/txtai/issues/409) for more on this issue.++----------++__Issue__++Error installing optional/extra dependencies such as `pipeline`++__Solution__++The default MacOS shell (zsh) and Windows Powershell require escaping square brackets++```+pip install 'txtai[pipeline]'+```diff --git a/docs/pipeline/data/textractor.md b/docs/pipeline/data/textractor.mdindex c05460f7..2b93df11 100644--- a/docs/pipeline/data/textractor.md+++ b/docs/pipeline/data/textractor.md@@ -5,6 +5,8 @@The Textractor pipeline extracts and splits text from documents. This pipeline uses either an [Apache Tika](https://github.com/chrismattmann/tika-python) backend (if Java is available) or [BeautifulSoup4](https://pypi.org/project/beautifulsoup4/).+_Note: BeautifulSoup4 only supports HTML documents, anything else requires Tika and Java to be installed._+## ExampleThe following shows a simple example using this pipeline.