Merge branch 'releases/2024/6' into DOCS-updating-links-to-GenAI-24.6

docs/articles_en/about-openvino/performance-benchmarks.rst

@@ -56,7 +56,6 @@ implemented in your solutions. Click the buttons below to see the chosen benchma
 
          :material-regular:`table_view;1.4em` LLM performance for AI PC
 
-.. uncomment under veryfication
    .. grid-item::
 
       .. button-link:: #

docs/articles_en/learn-openvino/llm_inference_guide/genai-guide-npu.rst

@@ -44,7 +44,7 @@ You select one of the methods by setting the ``--group-size`` parameter to eithe
       .. code-block:: console
          :name: group-quant
 
-         optimum-cli export openvino -m TinyLlama/TinyLlama-1.1B-Chat-v1.0 --weight-format int4 --sym --ratio 1.0 --group_size 128 TinyLlama-1.1B-Chat-v1.0
+         optimum-cli export openvino -m TinyLlama/TinyLlama-1.1B-Chat-v1.0 --weight-format int4 --sym --ratio 1.0 --group-size 128 TinyLlama-1.1B-Chat-v1.0
 
    .. tab-item:: Channel-wise quantization
 
@@ -63,12 +63,12 @@ You select one of the methods by setting the ``--group-size`` parameter to eithe
             If you want to improve accuracy, make sure you:
 
             1. Update NNCF: ``pip install nncf==2.13``
-            2. Use ``--scale_estimation --dataset=<dataset_name>`` and accuracy aware quantization ``--awq``:
+            2. Use ``--scale_estimation --dataset <dataset_name>`` and accuracy aware quantization ``--awq``:
 
                .. code-block:: console
                   :name: channel-wise-data-aware-quant
 
-                  optimum-cli export openvino -m meta-llama/Llama-2-7b-chat-hf --weight-format int4 --sym --group-size -1 --ratio 1.0 --awq --scale-estimation --dataset=wikitext2  Llama-2-7b-chat-hf
+                  optimum-cli export openvino -m meta-llama/Llama-2-7b-chat-hf --weight-format int4 --sym --group-size -1 --ratio 1.0 --awq --scale-estimation --dataset wikitext2  Llama-2-7b-chat-hf
 
 
       .. important::

docs/articles_en/learn-openvino/llm_inference_guide/genai-guide.rst

@@ -123,7 +123,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/image_generation>`__
+         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/image_generation>`__
 
       .. tab-item:: C++
          :sync: cpp
@@ -225,7 +225,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
                   }
 
          For more information, refer to the
-         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/image_generation/>`__
+         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/image_generation/>`__
 
 
 .. dropdown:: Speech Recognition
@@ -271,7 +271,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/whisper_speech_recognition/>`__.
+         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/whisper_speech_recognition/>`__.
 
       .. tab-item:: C++
          :sync: cpp
@@ -323,7 +323,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
             }
 
          For more information, refer to the
-         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/whisper_speech_recognition/>`__.
+         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/whisper_speech_recognition/>`__.
 
 
 .. dropdown:: Using GenAI in Chat Scenario
@@ -367,7 +367,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/text_generation/chat_sample/>`__.
+         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/chat_sample/>`__.
 
       .. tab-item:: C++
          :sync: cpp
@@ -415,8 +415,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/text_generation/chat_sample/>`__
-
+         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/chat_sample/>`__
 
 .. dropdown:: Using GenAI with Vision Language Models
 
@@ -483,7 +482,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/visual_language_chat>`__.
+         `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/visual_language_chat>`__.
 
       .. tab-item:: C++
          :sync: cpp
@@ -549,7 +548,7 @@ make sure to :doc:`install OpenVINO with GenAI <../../get-started/install-openvi
 
 
          For more information, refer to the
-         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/visual_language_chat/>`__
+         `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/visual_language_chat/>`__
 
 
 |
@@ -803,8 +802,7 @@ runs prediction of the next K tokens, thus repeating the cycle.
 
 
       For more information, refer to the
-      `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/text_generation/speculative_decoding_lm/>`__.
-
+      `Python sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/speculative_decoding_lm/>`__.
 
    .. tab-item:: C++
       :sync: cpp
@@ -859,12 +857,7 @@ runs prediction of the next K tokens, thus repeating the cycle.
 
 
       For more information, refer to the
-      `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/text_generation/speculative_decoding_lm/>`__
-
-
-
-
-
+      `C++ sample <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/speculative_decoding_lm/>`__
 
 
 

docs/articles_en/learn-openvino/llm_inference_guide/llm-inference-native-ov.rst

@@ -98,6 +98,17 @@ Learn more in Loading an LLM with OpenVINO.
 
    optimum-cli export openvino --convert-tokenizer --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 openvino_model
 
+.. note::
+
+   The current Optimum version can convert both the model and tokenizers. To do so, use the
+   standard call:
+
+   .. code-block:: py
+
+      optimum-cli export openvino --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 openvino_model
+
+
+
 Full OpenVINO Text Generation Pipeline
 ######################################################################
 
@@ -110,6 +121,7 @@ Use the model and tokenizer converted from the previous step:
 
    import numpy as np
    from openvino import compile_model
+   import openvino_tokenizers
 
    # Compile the tokenizer, model, and detokenizer using OpenVINO. These files are XML representations of the models optimized for OpenVINO
    compiled_tokenizer = compile_model("openvino_tokenizer.xml")
@@ -154,7 +166,7 @@ and appends it to the existing sequence.
    # Generate new tokens iteratively
    for idx in range(prompt_size, prompt_size + new_tokens_size):
        # Get output from the model
-       output = compiled_model(input_dict)["token_ids"]
+       output = compiled_model(input_dict)[0]
        # Update the input_ids with newly generated token
        input_dict["input_ids"][:, idx] = output[:, idx - 1]
        # Update the attention mask to include the new token

docs/articles_en/learn-openvino/llm_inference_guide/ov-tokenizers.rst

@@ -336,7 +336,7 @@ Additional Resources
 
 * `OpenVINO Tokenizers repo <https://github.com/openvinotoolkit/openvino_tokenizers>`__
 * `OpenVINO Tokenizers Notebook <https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/openvino-tokenizers>`__
-* `Text generation C++ samples that support most popular models like LLaMA 3 <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/greedy_causal_lm>`__
+* `Text generation C++ samples that support most popular models like LLaMA 3 <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/greedy_causal_lm>`__
 * `OpenVINO GenAI Repo <https://github.com/openvinotoolkit/openvino.genai>`__
 
 

docs/articles_en/openvino-workflow/model-optimization-guide/weight-compression.rst

@@ -354,7 +354,7 @@ To find the optimal weight compression parameters for a particular model, refer
 `example <https://github.com/openvinotoolkit/nncf/tree/develop/examples/llm_compression/openvino/tiny_llama_find_hyperparams>`__ ,
 where weight compression parameters are being searched from the subset of values.
 To speed up the search, a self-designed validation pipeline called
-`WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/llm_bench/python/who_what_benchmark>`__
+`WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/tools/who_what_benchmark>`__
 is used. The pipeline can quickly evaluate the changes in the accuracy of the optimized
 model compared to the baseline.
 
@@ -491,7 +491,7 @@ Additional Resources
 - `OpenVINO GenAI Repo <https://github.com/openvinotoolkit/openvino.genai>`__
   : Repository containing example pipelines that implement image and text generation
   tasks. It also provides a tool to benchmark LLMs.
-- `WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/llm_bench/python/who_what_benchmark>`__
+- `WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/tools/who_what_benchmark>`__
 - `NNCF GitHub <https://github.com/openvinotoolkit/nncf>`__
 - :doc:`Post-training Quantization <quantizing-models-post-training>`
 - :doc:`Training-time Optimization <compressing-models-during-training>`

docs/articles_en/openvino-workflow/running-inference/string-tensors.rst

@@ -12,7 +12,7 @@ Such a tensor is called a string tensor and can be passed as input or retrieved
 
 While this section describes basic API to handle string tensors, more practical examples that leverage both
 string tensors and OpenVINO tokenizer can be found in
-`GenAI Samples <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/greedy_causal_lm>`__.
+`GenAI Samples <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/greedy_causal_lm>`__.
 
 
 Representation
@@ -203,4 +203,4 @@ Additional Resources
 
 * Use `OpenVINO tokenizers <https://github.com/openvinotoolkit/openvino_contrib/tree/releases/2024/0/modules/custom_operations/user_ie_extensions/tokenizer/python>`__ to produce models that use string tensors to work with textual information as pre- and post-processing for the large language models.
 
-* Check out `GenAI Samples <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/greedy_causal_lm>`__ to see how string tensors are used in real-life applications.
+* Check out `GenAI Samples <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/greedy_causal_lm>`__ to see how string tensors are used in real-life applications.

docs/notebooks/multilora-image-generation-with-output.rst

@@ -210,7 +210,7 @@ generative models as it already includes all the core functionality.
 
 ``openvino_genai.Text2ImagePipeline`` class supports inference of
 `Diffusers
-models <https://github.com/openvinotoolkit/openvino.genai/blob/master/src/docs/SUPPORTED_MODELS.md#text-2-image-models>`__.
+models <https://github.com/openvinotoolkit/openvino.genai/blob/releases/2024/6/src/docs/SUPPORTED_MODELS.md#text-2-image-models>`__.
 For pipeline initialization, we should provide directory with converted
 by Optimum Intel pipeline and specify inference device. Optionally, we
 can provide configuration for LoRA Adapters using ``adapter_config``.

docs/notebooks/openvino-tokenizers-with-output.rst

@@ -548,6 +548,6 @@ Links
    Types <https://github.com/openvinotoolkit/openvino_tokenizers?tab=readme-ov-file#supported-tokenizer-types>`__
 -  `OpenVINO.GenAI repository with the C++ example of OpenVINO
    Tokenizers
-   usage <https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/greedy_causal_lm>`__
+   usage <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/cpp/greedy_causal_lm>`__
 -  `HuggingFace Tokenizers Comparison
    Table <https://github.com/openvinotoolkit/openvino_tokenizers?tab=readme-ov-file#output-match-by-model>`__

docs/notebooks/whisper-asr-genai-with-output.rst

@@ -30,7 +30,7 @@ converts the models to OpenVINO™ IR format. To simplify the user
 experience, we will use `OpenVINO Generate
 API <https://github.com/openvinotoolkit/openvino.genai>`__ for `Whisper
 automatic speech recognition
-scenarios <https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/python/whisper_speech_recognition/README.md>`__.
+scenarios <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/whisper_speech_recognition/README.md>`__.
 
 Installation Instructions
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -406,7 +406,7 @@ Run inference OpenVINO model with WhisperPipeline
 
 
 To simplify user experience we will use `OpenVINO Generate
-API <https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/python/whisper_speech_recognition/README.md>`__.
+API <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/whisper_speech_recognition/README.md>`__.
 Firstly we will create pipeline with ``WhisperPipeline``. You can
 construct it straight away from the folder with the converted model. It
 will automatically load the ``model``, ``tokenizer``, ``detokenizer``

docs/notebooks/whisper-subtitles-generation-with-output.rst

@@ -21,7 +21,7 @@ GitHub `repository <https://github.com/openai/whisper>`__.
 In this notebook, we will use Whisper model with `OpenVINO Generate
 API <https://github.com/openvinotoolkit/openvino.genai>`__ for `Whisper
 automatic speech recognition
-scenarios <https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/python/whisper_speech_recognition/README.md>`__
+scenarios <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/whisper_speech_recognition/README.md>`__
 to generate subtitles in a sample video. Additionally, we will use
 `NNCF <https://github.com/openvinotoolkit/nncf>`__ improving model
 performance by INT8 quantization. Notebook contains the following steps:
@@ -228,7 +228,7 @@ Whisper model.
    whisper_pipeline.png
 
 To simplify user experience we will use `OpenVINO Generate
-API <https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/python/whisper_speech_recognition/README.md>`__.
+API <https://github.com/openvinotoolkit/openvino.genai/tree/releases/2024/6/samples/python/whisper_speech_recognition/README.md>`__.
 Firstly we will create pipeline with ``WhisperPipeline``. You can
 construct it straight away from the folder with the converted model. It
 will automatically load the ``model``, ``tokenizer``, ``detokenizer``

docs/openvino_custom_sphinx_sitemap/openvino_custom_sphinx_sitemap/__init__.py

@@ -126,35 +126,38 @@ def process_coveo_meta(meta, url, link):
             if tag_name == 'ovdoctype':
                 ET.SubElement(namespace_element, tag_name).text = process_link(link)
             elif tag_name == 'ovcategory' and loc_element is not None:
-                ET.SubElement(namespace_element, tag_name).text = extract_hierarchy(loc_element.text)
+                ET.SubElement(namespace_element, tag_name).text = extract_categories(loc_element.text)
             elif tag_name == 'ovversion':
                 ET.SubElement(namespace_element, tag_name).text = tag_value
 
 def process_link(link):
     if '/' in link:
-        return link.split('/')[0].replace("-", " ")
-    return link.split('.html')[0].replace("-", " ")
+        return format_segment(link.split('/')[0].replace("-", " "))
+    return format_segment(link.split('.html')[0].replace("-", " "))
 
-def extract_hierarchy(link):
+def extract_categories(link):
     path = link.split("://")[-1]
     segments = path.split('/')[1:]
     if segments and segments[-1].endswith('.html'):
         segments = segments[:-1]
 
+    if segments:
+        segments = segments[1:]
+
     if segments and '.' in segments[0]:
         year, *rest = segments[0].split('.')
         if year.isdigit() and len(year) == 4:
             segments[0] = year
 
     segments = [format_segment(segment) for segment in segments]
 
-    hierarchy = []
-    for i in range(1, len(segments) + 1):
-        hierarchy.append('|'.join(segments[:i]))
-
-    return ';'.join(hierarchy)
+    if segments:
+        hierarchy = ['|'.join(segments[:i]) for i in range(1, len(segments) + 1)]
+        return ';'.join(hierarchy)
+    
+    return "No category"
 
 def format_segment(segment):
-    if segment == 'c_cpp_api': segment = 'c/c++_api'
+    if segment == 'c_cpp_api': segment = 'C/C++_api'
 
     return ' '.join(word.capitalize() for word in segment.replace('-', ' ').replace('_', ' ').split())

docs/sphinx_setup/conf.py

@@ -187,13 +187,11 @@
 html_static_path = ['_static']
 
 html_css_files = [
-    'css/custom.css',
     'css/openvino_sphinx_theme.css',
     'css/button.css',
     'css/input.css',
     'css/textfield.css',
     'css/tabs.css',
-    'css/coveo_custom.css',
     'https://cdn.jsdelivr.net/npm/@splidejs/[email protected]/dist/css/splide.min.css',
 ]