[DOCS] Add TextRerankPipeline to readme.md

README.md

@@ -46,6 +46,7 @@ OpenVINO™ GenAI library provides very lightweight C++ and Python APIs to run t
  - [Speech recognition using Whisper family models](#speech-to-text)
  - [Text-to-speech generation using SpeechT5 TTS models](#text-to-speech)
  - [Text embedding for Retrieval-Augmented Generation (RAG)](#text-embedding), for example, compute embeddings for documents and queries to enable efficient retrieval in RAG workflows.
+ - [Text reranking for Retrieval-Augmented Generation (RAG)](#text-rerank), for example, reorder candidate documents by semantic relevance to a query to improve retrieval quality in RAG workflows.
 
 Library efficiently supports LoRA adapters for Text and Image generation scenarios:
 - Load multiple adapters per model
@@ -513,7 +514,7 @@ int main(int argc, char* argv[]) {
 
 ```sh
 # Download and convert the BAAI/bge-small-en-v1.5 model to OpenVINO format
-optimum-cli export openvino --trust-remote-code --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
+optimum-cli export openvino --task feature-extraction --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
 ```
 
 ### Compute embeddings using TextEmbeddingPipeline API in Python
@@ -567,6 +568,53 @@ int main(int argc, char* argv[]) {
 ```
 </details>
 
+<a id="text-rerank"></a>
+
+## Text Reranking
+<details>
+
+### Converting and preparing a text reranking model from Hugging Face library
+
+```sh
+optimum-cli export openvino --task text-classification --model cross-encoder/ms-marco-MiniLM-L6-v2 cross-encoder/ms-marco-MiniLM-L6-v2
+```
+
+### Rerank documents using TextRerankPipeline API in Python
+
+```python
+import openvino_genai
+
+pipeline = openvino_genai.TextRerankPipeline("./cross-encoder/ms-marco-MiniLM-L6-v2", "CPU", top_n=3)
+
+rerank_result = pipeline.rerank(query, documents)
+
+print("Reranked documents:")
+for index, score in rerank_result:
+    print(f"Document {index} (score: {score:.4f}): {documents[index]}")
+```
+
+### Rerank documents using TextRerankPipeline API in C++
+
+```cpp
+#include "openvino/genai/rag/text_rerank_pipeline.hpp"
+#include <iostream>
+
+int main(int argc, char* argv[]) {
+    std::vector<std::string> documents(argv + 3, argv + argc);
+    std::string models_path = argv[1], query = argv[2];
+
+    ov::genai::TextRerankPipeline pipeline(models_path, "CPU", ov::genai::top_n(3));
+
+    auto rerank_result = pipeline.rerank(query, documents);
+
+    std::cout << "Reranked documents:\n";
+    for (const auto& [index, score] : rerank_result) {
+        std::cout << "Document " << index << " (score: " << score << "): " << documents[index] << '\n';
+    }
+}
+```
+</details>
+
 ## Additional materials
 
 - [List of supported models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/)

samples/cpp/rag/README.md

@@ -15,13 +15,13 @@ pip install --upgrade-strategy eager -r ../../export-requirements.txt
 To export text embedding model run Optimum CLI command:
 
 ```sh
-optimum-cli export openvino --trust-remote-code --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
+optimum-cli export openvino --task feature-extraction --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
 ```
 
 To export text reranking model run Optimum CLI command:
 
 ```sh
-optimum-cli export openvino --trust-remote-code --model cross-encoder/ms-marco-MiniLM-L6-v2 cross-encoder/ms-marco-MiniLM-L6-v2
+optimum-cli export openvino --task text-classification --model cross-encoder/ms-marco-MiniLM-L6-v2 cross-encoder/ms-marco-MiniLM-L6-v2
 ```
 
 

samples/js/rag/README.md

@@ -10,7 +10,7 @@ Install [../../export-requirements.txt](../../export-requirements.txt) to conver
 
 ```sh
 pip install --upgrade-strategy eager -r ../../export-requirements.txt
-optimum-cli export openvino --trust-remote-code --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
+optimum-cli export openvino --task feature-extraction --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
 ```
 
 ## Sample Descriptions

samples/python/rag/README.md

@@ -15,13 +15,13 @@ pip install --upgrade-strategy eager -r ../../export-requirements.txt
 To export text embedding model run Optimum CLI command:
 
 ```sh
-optimum-cli export openvino --trust-remote-code --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
+optimum-cli export openvino --task feature-extraction --model BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
 ```
 
 To export text reranking model run Optimum CLI command:
 
 ```sh
-optimum-cli export openvino --trust-remote-code --model cross-encoder/ms-marco-MiniLM-L6-v2 cross-encoder/ms-marco-MiniLM-L6-v2
+optimum-cli export openvino --task text-classification --model cross-encoder/ms-marco-MiniLM-L6-v2 cross-encoder/ms-marco-MiniLM-L6-v2
 ```
 
 Alternatively, do it in Python code:
@@ -33,7 +33,7 @@ from transformers import AutoTokenizer
 
 output_dir = "embedding_model"
 
-model = OVModelForFeatureExtraction.from_pretrained("BAAI/bge-small-en-v1.5", export=True, trust_remote_code=True)
+model = OVModelForFeatureExtraction.from_pretrained("BAAI/bge-small-en-v1.5", export=True)
 model.save_pretrained(output_dir)
 
 tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-small-en-v1.5")

site/docs/use-cases/text-embedding/index.mdx

@@ -11,7 +11,7 @@ import UsageOptionsSection from './_sections/_usage_options/index.mdx';
 <ConvertModelSection>
     Download and convert a text embedding model (e.g. [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)) to OpenVINO format from Hugging Face:
 
-    <OptimumCLI model='BAAI/bge-small-en-v1.5' outputDir='bge-small-en-v1_5_ov' trustRemoteCode />
+    <OptimumCLI model='BAAI/bge-small-en-v1.5' outputDir='bge-small-en-v1_5_ov' task='feature-extraction' />
 
     See all supported [Text Embedding Models](/docs/supported-models/#text-embeddings-models).
 </ConvertModelSection>

site/docs/use-cases/text-rerank/index.mdx

@@ -10,7 +10,7 @@ import RunModelSection from './_sections/_run_model/index.mdx';
 <ConvertModelSection>
     Download and convert a reranker model (e.g. [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2)) to OpenVINO format from Hugging Face:
 
-    <OptimumCLI model='cross-encoder/ms-marco-MiniLM-L6-v2' outputDir='cross-encoder/ms-marco-MiniLM-L6-v2' trustRemoteCode />
+    <OptimumCLI model='cross-encoder/ms-marco-MiniLM-L6-v2' outputDir='cross-encoder/ms-marco-MiniLM-L6-v2' task='text-classification' />
 
     See all supported [Reranker Models](/docs/supported-models/#text-rerank-models).
 </ConvertModelSection>