* Initial commit for integrating Optimum Intel with v0.10

Based on the Optimum integration.

* Test

* Dependencies

* Neural compressor code

* Notebook example

* Lock file

* Add UpTrain Callback Handler

* Add logging

* Add note for project_name prefix

* Minor fixes

* Add explanations

* Add showcase

* Add callback to uptrain.md

* update import

* linter

* Update .gitignore file to ignore .venv and __pycache__ directories

* Fix imports

* create llama-index-callback-uptrain

* Update UpTrainCallback.ipynb

* Update README.md

* Run pants tailor

* llamaindex cli package

* BUILD to pass tests

* generate pants BUILD files

* add skip tests

* use llamaindex-cli name

* CHANGELOG

* Fix the perf issue in building nodes from splits.

Create the `relationships` object only once. Otherwise, it recomputes the whole text's hash for every node. It is very inefficient for long text.

An alternative approach would be to cache the hash property. However, it wasn't so straightforward as `Document` isn't a cacheable type. I also do not know Python very well, maybe it would be enough to store a simple null and if it isn't null, then don't recompute? However, the most important reason is I'm not sure about the side effects and the existing assumption that the node is mutable and the hash always reflects the state during the call (unless we modify the object in multiple threads). This change doesn't break any assumptions. If the document was modified while we were creating nodes extracted from it, something would be very wrong.

Benchmarks taken on a document attached to the bug:

Before: Execution time for build_nodes_from_splits: 53.69 seconds

After: Execution time for build_nodes_from_splits: 0.18 seconds

* Fix the formatting

* allowing connection to a TLS-secured with untrusted certificate MinIO instance

* updated README for MinIO reader

* cert_check should default to True for MinIO reader

---------

Co-authored-by: Ferdinando Simonetti <info@fsimonetti.info>

* remove wrong clip; add correct one

* CHANGELOG

* remove clip as can't publish pypi packwage with git dep

* remove clip as can't publish pypi packwage with git dep

Fix broken core link from integration docs

* initial working version of presidio integration

* added presidio with mapping

* added deanonymize mapping to validation stage

* linting and formatting

* moved presidio to postprocessor integration

* removing legacy files

* added base tests and more project definitions

* added and edited build files

* added a simple example to notebook

---------

Co-authored-by: Roey Ben Chaim <roeybenchaim@Roeys-MacBook-Pro.local>

add retriever_mode param when constructing KGTableRetriever

* Add __del__ at Vllm for deleting model

* cr

* updated example, pkg breakage due to refactor errors fixed

* typos

* nb clean

* output restored

* formatting

* typo

version bumps; add changelogs

* Add Corrective RAG LlamaPack

* Update with review suggestions

* Remove requirements.txt file

* Update BUILD

* Update examples

* Testing done

fix the bug on vector_search_profile default(this profile did not exist) and add the possibility to choose language_analyzer of searchable fields, now on v0.10.3 format (#10675)

add FunctionComponent alias

Add maintainers (i.e. authors) and keywords to pyproject.toml from library.json (readers, tools, packs) (#10668)

port over authors and keywords from llamahub library json

* add OpensearchVectorClient

* fix OpensearchVectorClient import

* version bump; CHANGELOG