Add bookmarks to README.md and generate new notebook

Add bookmarks and new example notebooks to the `README.md` for better navigation.

* **README.md**
  - Add bookmarks for "Classify files Example" and "Splitting Files Example" sections.
  - Update the table to include links to the new example notebooks.

* **classification.ipynb**
  - Add a new notebook demonstrating how to use ExtractThinker for classifying documents.
  - Include setup instructions, API key configuration, document loader creation, extractor creation, and data extraction.

* **splitting.ipynb**
  - Add a new notebook demonstrating how to split and process documents using ExtractThinker.
  - Include setup instructions, API key configuration, document loader creation, extractor creation, and data extraction.

---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/enoch3712/ExtractThinker?shareId=XXXX-XXXX-XXXX-XXXX).

README.md

@@ -116,6 +116,8 @@ The `extract_thinker` project is inspired by the LangChain ecosystem, featuring
 | Notebook | Description |
 |----------|-------------|
 | [Basic Usage](examples/notebooks/basic_example.ipynb) | Basic usage of ExtractThinker with PyPDF loader and GPT-4o-mini for invoice data extraction |
+| [Classify files Example](classification.ipynb) | Example of classifying files using ExtractThinker |
+| [Splitting Files Example](splitting.ipynb) | Example of splitting files using ExtractThinker |
 
 ## Why Just Not LangChain?
 While LangChain is a generalized framework designed for a wide array of use cases, extract_thinker is specifically focused on Intelligent Document Processing (IDP). Although achieving 100% accuracy in IDP remains a challenge, leveraging LLMs brings us significantly closer to this goal.
@@ -140,4 +142,4 @@ Júlio Almeida
 This project is licensed under the Apache License 2.0. See the LICENSE file for more details.
 
 ## Contact
-For any questions or issues, please open an issue on the GitHub repository.
+For any questions or issues, please open an issue on the GitHub repository.