[PR #793] [MERGED] feat: add table extraction for LlamaParse as CSV files #864

Closed
opened 2026-02-16 00:19:20 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/run-llama/llama_cloud_services/pull/793
Author: @AstraBert
Created: 7/16/2025
Status: Merged
Merged: 7/16/2025
Merged by: @AstraBert

Base: mainHead: clelia/add-table-extraction


📝 Commits (5)

  • 2afd126 feat: add table extraction for LlamaParse as CSV files
  • 0714b12 chore: poetry lock
  • 0bb0bb8 chore: add tests
  • d8a963b fix: handle the case where no tables are present
  • e619a5f chore: implement suggestions

📊 Changes

4 files changed (+76 additions, -3 deletions)

View changed files

📝 llama_cloud_services/parse/base.py (+11 -0)
📝 llama_cloud_services/parse/utils.py (+31 -1)
📝 pyproject.toml (+1 -1)
📝 tests/parse/test_utils.py (+33 -1)

📄 Description

Combining markdown-analysis and pandas, we add the possibility for users to directly get their tables from LlamaParse JSON results.

The idea is:

parser = LlamaParse(api_key="llx-***", result_type="markdown")
result = parser.get_json_result("path/to/file")
tables = parser.get_tables(json_result=result, download_path="tables/")

This will save the tables in the markdown text as CSV files in the tables folder.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/run-llama/llama_cloud_services/pull/793 **Author:** [@AstraBert](https://github.com/AstraBert) **Created:** 7/16/2025 **Status:** ✅ Merged **Merged:** 7/16/2025 **Merged by:** [@AstraBert](https://github.com/AstraBert) **Base:** `main` ← **Head:** `clelia/add-table-extraction` --- ### 📝 Commits (5) - [`2afd126`](https://github.com/run-llama/llama_cloud_services/commit/2afd126b5283bbf515b90bcb75e87cbf7bcdb057) feat: add table extraction for LlamaParse as CSV files - [`0714b12`](https://github.com/run-llama/llama_cloud_services/commit/0714b127f4dd554f8e5b2d8edb8d6757410b246c) chore: poetry lock - [`0bb0bb8`](https://github.com/run-llama/llama_cloud_services/commit/0bb0bb844d1670688b5612552af1d4d46655a533) chore: add tests - [`d8a963b`](https://github.com/run-llama/llama_cloud_services/commit/d8a963b5b4d16d363d9918924213a5be1a85f86f) fix: handle the case where no tables are present - [`e619a5f`](https://github.com/run-llama/llama_cloud_services/commit/e619a5f75e639de475ad37667e5bc5dab0061aa7) chore: implement suggestions ### 📊 Changes **4 files changed** (+76 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `llama_cloud_services/parse/base.py` (+11 -0) 📝 `llama_cloud_services/parse/utils.py` (+31 -1) 📝 `pyproject.toml` (+1 -1) 📝 `tests/parse/test_utils.py` (+33 -1) </details> ### 📄 Description Combining [`markdown-analysis`](https://pypi.org/project/markdown-analysis/) and `pandas`, we add the possibility for users to directly get their tables from LlamaParse JSON results. The idea is: ```python parser = LlamaParse(api_key="llx-***", result_type="markdown") result = parser.get_json_result("path/to/file") tables = parser.get_tables(json_result=result, download_path="tables/") ``` This will save the tables in the markdown text as CSV files in the `tables` folder. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-16 00:19:20 -05:00
yindo closed this issue 2026-02-16 00:19:21 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#864