* unify integration with llama index

* adding docs

* updating notebook

* formatting fixes in notebook

* improve examples

* formatting fix

* reducing verbosity

* adding live benchmark link

* notebook edits

* formatting fix

* Update unify.ipynb

small changes to the text

* bigger fonts

* tweaking font size in unify notebook

* minor unify nb edit

* add dependencies

* add notebook to index

* changes to notebook

* change docs after refactor

* add test

* format + lint

* add poetry lock

* improve readme

* Fix linting issues

* Fix CI errors

* fix linting errors

---------

Co-authored-by: Aparajith Raghuvir <aparajithr21@gmail.com>
Co-authored-by: aparajith21 <58738384+aparajith21@users.noreply.github.com>
Co-authored-by: guillesanbri <guillesanbri@hotmail.com>
Co-authored-by: Anwaar Khalid <shahanwaar.khalid8@gmail.com>

Deprecate mode() in favor of __init__(base_url=...) for NVIDIA, NVIDIAEmbedding, NVIDIARerank (#13572)

* deprecate NVIDIA().mode(...), use NVIDIA(...) instead

* bump version to 0.1.3

* deprecate NVIDIAEmbedding().mode(...), use NVIDIAEmbedding(...) instead

* bump version to 0.1.2

* deprecate NVIDIARerank().mode(...), use NVIDIARerank(...) instead

* bump version to 0.1.3

vbump here

* vbump

* wip

* rm openvino tests

if unset the service decides and picks a value small enough that users report the model is broken or not accurate

Bump jinja2 from 3.1.3 to 3.1.4 in /llama-index-integrations/llms/llama-index-llms-friendli (#13304)

Bump tqdm from 4.66.2 to 4.66.3 in /llama-index-integrations/llms/llama-index-llms-friendli (#13258)

* Integrate

* Changes based on comments

* Run pants tailor

* Properly extract and pass logprobs

* Add a simple test

* Add a usage section

* Fix silly mistake

* Add mistralrs as a dependancy

* Fix extract logprobs and update api

* Update for new version

* Update version

* Prettier

* Fix typing

* Remove unnecessary in docs BUILD

* Adding claude 3 opus to BedRock integration

* Increment version