mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-02-11 15:25:16 -05:00
e596ea87cbae55eedba3bc58f144702e9e310504
7 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Nicholas Tindle
|
cb08def96c |
feat(blocks): Add Google Docs integration blocks (#11608)
Introduces a new module with blocks for Google Docs operations,
including reading, creating, appending, inserting, formatting,
exporting, sharing, and managing public access for Google Docs. Updates
dependencies in pyproject.toml and poetry.lock to support these
features.
https://github.com/user-attachments/assets/3597366b-a9eb-4f8e-8a0a-5a0bc8ebc09b
<!-- Clearly explain the need for these changes: -->
### Changes 🏗️
Adds lots of basic docs tools + a dependency to use them with markdown
Block | Description | Key Features
-- | -- | --
Read & Create | |
GoogleDocsReadBlock | Read content from a Google Doc | Returns text
content, title, revision ID
GoogleDocsCreateBlock | Create a new Google Doc | Title, optional
initial content
GoogleDocsGetMetadataBlock | Get document metadata | Title, revision ID,
locale, suggested modes
GoogleDocsGetStructureBlock | Get document structure with indexes | Flat
segments or detailed hierarchy; shows start/end indexes
Plain Text Operations | |
GoogleDocsAppendPlainTextBlock | Append plain text to end | No
formatting applied
GoogleDocsInsertPlainTextBlock | Insert plain text at position |
Requires index; no formatting
GoogleDocsFindReplacePlainTextBlock | Find and replace plain text |
Case-sensitive option; no formatting on replacement
Markdown Operations | (ideal for LLM/AI output) |
GoogleDocsAppendMarkdownBlock | Append Markdown to end | Full formatting
via gravitas-md2gdocs
GoogleDocsInsertMarkdownAtBlock | Insert Markdown at position | Requires
index
GoogleDocsReplaceAllWithMarkdownBlock | Replace entire doc with Markdown
| Clears and rewrites
GoogleDocsReplaceRangeWithMarkdownBlock | Replace index range with
Markdown | Requires start/end index
GoogleDocsReplaceContentWithMarkdownBlock | Find text and replace with
Markdown | Text-based search; great for templates
Structural Operations | |
GoogleDocsInsertTableBlock | Insert a table | Rows/columns OR content
array; optional Markdown in cells
GoogleDocsInsertPageBreakBlock | Insert a page break | Position index (0
= end)
GoogleDocsDeleteContentBlock | Delete content range | Requires start/end
index
GoogleDocsFormatTextBlock | Apply formatting to text range | Bold,
italic, underline, font size/color, etc.
Export & Sharing | |
GoogleDocsExportBlock | Export to different formats | PDF, DOCX, TXT,
HTML, RTF, ODT, EPUB
GoogleDocsShareBlock | Share with specific users | Reader, commenter,
writer, owner roles
GoogleDocsSetPublicAccessBlock | Set public access level | Private,
anyone with link (view/comment/edit)
<!-- Concisely describe all of the changes made in this pull request:
-->
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Build, run, verify, and upload a block super test
- [x] [Google Docs Super
Agent_v8.json](https://github.com/user-attachments/files/24134215/Google.Docs.Super.Agent_v8.json)
works
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Chores**
* Updated backend dependencies.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds end-to-end Google Docs capabilities under
`backend/blocks/google/docs.py`, including rich Markdown support.
>
> - New blocks: read/create docs; plain-text
`append`/`insert`/`find_replace`/`delete`; text `format`;
`insert_table`; `insert_page_break`; `get_metadata`; `get_structure`
> - Markdown-powered blocks (via `gravitas_md2gdocs.to_requests`):
`append_markdown`, `insert_markdown_at`, `replace_all_with_markdown`,
`replace_range_with_markdown`, `replace_content_with_markdown`
> - Export and sharing: `export` (PDF/DOCX/TXT/HTML/RTF/ODT/EPUB),
`share` (user roles), `set_public_access`
> - Dependency updates: add `gravitas-md2gdocs` to `pyproject.toml` and
update `poetry.lock`
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
|
||
|
lif
|
266e0d79d4 |
fix(blocks): add YouTube Shorts URL support (#11659)
## Summary Added support for parsing YouTube Shorts URLs (`youtube.com/shorts/...`) in the TranscribeYoutubeVideoBlock to extract video IDs correctly. ## Changes - Modified `_extract_video_id` method in `youtube.py` to handle Shorts URL format - Added test cases for YouTube Shorts URL extraction ## Related Issue Fixes #11500 ## Test Plan - [x] Added unit tests for YouTube Shorts URL extraction - [x] Verified existing YouTube URL formats still work - [x] CI should pass all existing tests --------- Co-authored-by: Ubbe <hi@ubbe.dev> |
||
|
Swifty
|
7d53c0de27 |
fix(backend): Fix Youtube blocking our cloud ips (#11456)
Youtube can blocks cloud ips causing the youtube transcribe blocks to
not work. This PR adds webshare proxy to get around this issue
### Changes 🏗️
- add webshare proxy to youtube transcribe block
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] I have tested this works locally using the proxy
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Routes YouTube transcript fetching through Webshare proxy using
user/password credentials, wiring in provider enum, settings, default
credentials, and updated tests.
>
> - **Blocks** (`backend/blocks/youtube.py`):
> - Use `WebshareProxyConfig` with `YouTubeTranscriptApi` to fetch
transcripts via proxy.
> - Add `credentials` input (`user_password` for `webshare_proxy`);
include test credentials and mocks.
> - Update method signatures: `get_transcript(video_id, credentials)`
and `run(..., *, credentials, ...)`.
> - Change description to indicate proxy usage; add logging.
> - **Integrations**:
> - Providers (`backend/integrations/providers.py`): add
`ProviderName.WEBSHARE_PROXY`.
> - Credentials store (`backend/integrations/credentials_store.py`): add
`webshare_proxy` `UserPasswordCredentials`; include in
`DEFAULT_CREDENTIALS` and conditionally in `get_all_creds`.
> - **Settings** (`backend/util/settings.py`): add secrets
`webshare_proxy_username` and `webshare_proxy_password`.
> - **Tests** (`test/blocks/test_youtube.py`): update to pass
credentials and assert proxy config; add custom-credentials test; adjust
fallback/priority tests.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
|
||
|
Copilot
|
90af8f8e1a |
feat(backend): Add language fallback for YouTube transcription block (#11057)
## Problem The YouTube transcription block would fail when attempting to transcribe videos that only had transcripts available in non-English languages. Even when usable transcripts existed in other languages, the block would raise a `NoTranscriptFound` error because it only requested English transcripts. **Example video that would fail:** https://www.youtube.com/watch?v=3AMl5d2NKpQ (only has Hungarian transcripts) **Error message:** ``` Could not retrieve a transcript for the video https://www.youtube.com/watch?v=3AMl5d2NKpQ! No transcripts were found for any of the requested language codes: ('en',) For this video (3AMl5d2NKpQ) transcripts are available in the following languages: (GENERATED) - hu ("Hungarian (auto-generated)") ``` ## Solution Implemented intelligent language fallback in the `TranscribeYoutubeVideoBlock.get_transcript()` method: 1. **First**, tries to fetch English transcript (maintains backward compatibility) 2. **If English unavailable**, lists all available transcripts and selects the first one using this priority: - Manually created transcripts (any language) - Auto-generated transcripts (any language) 3. **Only fails** if no transcripts exist at all **Example behavior:** ```python # Before: Video with only Hungarian transcript get_transcript("3AMl5d2NKpQ") # ❌ Raises NoTranscriptFound # After: Video with only Hungarian transcript get_transcript("3AMl5d2NKpQ") # ✅ Returns Hungarian transcript ``` ## Changes - **Modified** `backend/blocks/youtube.py`: Added try-catch logic to fallback to any available language when English is not found - **Added** `test/blocks/test_youtube.py`: Comprehensive test suite covering URL extraction, language fallback, transcript preferences, and error handling (7 tests) - **Updated** `docs/content/platform/blocks/youtube.md`: Documented the language fallback behavior and transcript priority order ## Testing - ✅ All 7 new unit tests pass - ✅ Block integration test passes - ✅ Full test suite: 621 passed, 0 failed (no regressions) - ✅ Code formatting and linting pass ## Impact This fix enables the YouTube transcription block to work with international content while maintaining full backward compatibility: - ✅ Videos in any language can now be transcribed - ✅ English is still preferred when available - ✅ No breaking changes to existing functionality - ✅ Graceful degradation to available languages Fixes #10637 Fixes https://linear.app/autogpt/issue/OPEN-2626 > [!WARNING] > > <details> > <summary>Firewall rules blocked me from connecting to one or more addresses (expand for details)</summary> > > #### I tried to connect to the following addresses, but was blocked by firewall rules: > > - `www.youtube.com` > - Triggering command: `/home/REDACTED/.cache/pypoetry/virtualenvs/autogpt-platform-backend-Ajv4iu2i-py3.11/bin/python3` (dns block) > > If you need me to access, download, or install something from one of these locations, you can either: > > - Configure [Actions setup steps](https://gh.io/copilot/actions-setup-steps) to set up my environment, which run before the firewall is enabled > - Add the appropriate URLs or hosts to the custom allowlist in this repository's [Copilot coding agent settings](https://github.com/Significant-Gravitas/AutoGPT/settings/copilot/coding_agent) (admins only) > > </details> <!-- START COPILOT CODING AGENT SUFFIX --> <details> <summary>Original prompt</summary> > Issue Title: if theres only one lanague available for transcribe youtube return that langage not an error > Issue Description: `Could not retrieve a transcript for the video https://www.youtube.com/watch?v=3AMl5d2NKpQ! This is most likely caused by: No transcripts were found for any of the requested language codes: ('en',) For this video (3AMl5d2NKpQ) transcripts are available in the following languages: (MANUALLY CREATED) None (GENERATED) - hu ("Hungarian (auto-generated)") (TRANSLATION LANGUAGES) None If you are sure that the described cause is not responsible for this error and that a transcript should be retrievable, please create an issue at https://github.com/jdepoix/youtube-transcript-api/issues. Please add which version of youtube_transcript_api you are using and provide the information needed to replicate the error. Also make sure that there are no open issues which already describe your problem!` you can use this video to test: [https://www.youtube.com/watch?v=3AMl5d2NKpQ\`](https://www.youtube.com/watch?v=3AMl5d2NKpQ%60) > Fixes https://linear.app/autogpt/issue/OPEN-2626/if-theres-only-one-lanague-available-for-transcribe-youtube-return > > > Comment by User : > This thread is for an agent session with githubcopilotcodingagent. > > Comment by User : > This thread is for an agent session with githubcopilotcodingagent. > > Comment by User : > This comment thread is synced to a corresponding [GitHub issue](https://github.com/Significant-Gravitas/AutoGPT/issues/10637). All replies are displayed in both locations. > > </details> <!-- START COPILOT CODING AGENT TIPS --> --- ✨ Let Copilot coding agent [set things up for you](https://github.com/Significant-Gravitas/AutoGPT/issues/new?title=✨+Set+up+Copilot+instructions&body=Configure%20instructions%20for%20this%20repository%20as%20documented%20in%20%5BBest%20practices%20for%20Copilot%20coding%20agent%20in%20your%20repository%5D%28https://gh.io/copilot-coding-agent-tips%29%2E%0A%0A%3COnboard%20this%20repo%3E&assignees=copilot) — coding agent works faster and does higher quality work when set up for your repo. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: ntindle <8845353+ntindle@users.noreply.github.com> Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co> |
||
|
Nicholas Tindle
|
b08761816a |
feat(backend): add getting user profile, drafts, update send email to use mulitple to, cc, bcc (#10482)
Need: The Gmail integration had several parsing issues that were causing data loss and workflow incompatibilities: 1. Email recipient parsing only captured the first recipient, losing CC/BCC and multiple TO recipients 2. Email body parsing was inconsistent between blocks, sometimes showing "This email does not contain a readable body" for valid emails 3. Type mismatches between blocks caused serialization issues when connecting them in workflows (lists being converted to string representations like "[\"email@example.com\"]") # Changes 🏗️ 1. Enhanced Email Model: - Added cc and bcc fields to capture all recipients - Changed to field from string to list for consistency - Now captures all recipients instead of just the first one 2. Improved Email Parsing: - Updated GmailReadBlock and GmailGetThreadBlock to parse all recipients using getaddresses() - Unified email body parsing logic across blocks with robust multipart handling - Added support for HTML to plain text conversion - Fixed handling of emails with attachments as body content 3. Fixed Block Compatibility: - Updated GmailSendBlock and GmailCreateDraftBlock to accept lists for recipient fields - Added validation to ensure at least one recipient is provided - All blocks now consistently use lists for recipient fields, preventing serialization issues 4. Updated Test Data: - Modified all test inputs/outputs to use the new list format for recipients - Ensures tests reflect the new data structure # Checklist 📋 For code changes: - I have clearly listed my changes in the PR description - I have made a test plan - I have tested my changes according to the test plan: - Run existing Gmail block unit tests with poetry run test - Create a workflow that reads emails with multiple recipients and verify all TO, CC, BCC recipients are captured - Test email body parsing with plain text, HTML, and multipart emails - Connect GmailReadBlock → GmailSendBlock in a workflow and verify recipient data flows correctly - Connect GmailReplyBlock → GmailSendBlock and verify no serialization errors occur - Test sending emails with multiple recipients via GmailSendBlock - Test creating drafts with multiple recipients via GmailCreateDraftBlock - Verify backwards compatibility by testing with single recipient strings (should now require lists) - Create from scratch and execute an agent with at least 3 blocks - Import an agent from file upload, and confirm it executes correctly - Upload agent to marketplace - Import an agent from marketplace and confirm it executes correctly - Edit an agent from monitor, and confirm it executes correctly # Breaking Change Note: The to field in GmailSendBlock and GmailCreateDraftBlock now requires a list instead of accepting both string and list. Existing workflows using strings will need to be updated to use lists (e.g., ["email@example.com"] instead of "email@example.com"). --------- Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co> |
||
|
Zamil Majdy
|
423b22214a |
feat(blocks): Add Excel support to ReadSpreadsheetBlock and introduced FileReadBlock (#10393)
This PR adds Excel file support to CSV processing and enhances text file reading capabilities. ### Changes 🏗️ **ReadSpreadsheetBlock (formerly ReadCsvBlock):** - Renamed `ReadCsvBlock` to `ReadSpreadsheetBlock` for better clarity - Added Excel file support (.xlsx, .xls) with automatic conversion to CSV using pandas - Enhanced parameter `file_in` to `file_input` for consistency - Excel files are automatically detected by extension and converted to CSV format - Maintains all existing CSV processing functionality (delimiters, headers, etc.) - Graceful error handling when pandas library is not available **FileReadBlock:** - Enhanced text file reading with advanced chunking capabilities - Added parameters: `skip_size`, `skip_rows`, `row_limit`, `size_limit`, `delimiter` - Supports both character-based and row-based processing - Chunked output for large files based on size limits - Proper file handling with UTF-8 and latin-1 encoding fallbacks - Uses `store_media_file` for secure file processing (URLs, data URIs, local paths) - Fixed test input to use data URI instead of non-existent file **General Improvements:** - Consistent parameter naming across blocks (`file_input`) - Enhanced error handling and validation - Comprehensive test coverage - All existing functionality preserved ### Checklist 📋 #### For code changes: - [x] I have clearly listed my changes in the PR description - [x] I have made a test plan - [x] I have tested my changes according to the test plan: - [x] Both ReadSpreadsheetBlock and FileReadBlock instantiate correctly - [x] ReadSpreadsheetBlock processes CSV data with existing functionality - [x] FileReadBlock reads text files with data URI input - [x] All block tests pass (457 passed, 83 skipped) - [x] No linting errors in modified files - [x] Excel support gracefully handles missing pandas dependency #### For configuration changes: - [ ] `.env.example` is updated or already compatible with my changes - [ ] `docker-compose.yml` is updated or already compatible with my changes - [ ] I have included a list of my configuration changes in the PR description (under **Changes**) *Note: No configuration changes required for this PR.* |
||
|
Tejas Dharani
|
db1f034544 |
Fix Gmail body parsing for multipart messages (#9863) (#10071)
<!-- Clearly explain the need for these changes: --> The `GmailReadBlock._get_email_body()` method was only inspecting the top-level payload and a single `text/plain` part, causing it to return the fallback string "This email does not contain a text body." for most Gmail messages. This occurred because Gmail messages are typically wrapped in `multipart/alternative` or other multipart containers, which the original implementation couldn't handle. This critical issue made the Gmail integration unusable for reading email body content, as virtually every real Gmail message uses multipart MIME structures. <!-- Concisely describe all of the changes made in this pull request: --> ### Changes #### Core Implementation: - **Replaced simple `_get_email_body()` with recursive multipart parser** that can walk through nested MIME structures - **Added `_walk_for_body()` method** for recursive traversal of email parts with depth limiting (max 10 levels) - **Implemented safe base64 decoding** with automatic padding correction in `_decode_base64()` - **Added attachment body support** via `_download_attachment_body()` for emails where body content is stored as attachments #### Email Format Support: - **HTML to text conversion** using `html2text` library for HTML-only emails - **Multipart/alternative handling** with preference for `text/plain` over `text/html` - **Nested multipart structure support** (e.g., `multipart/mixed` containing `multipart/alternative`) - **Single-part email support** (maintains backward compatibility) #### Dependencies & Testing: - **Added `html2text = "^2024.2.26"`** to `pyproject.toml` for HTML conversion - **Created comprehensive unit tests** in `test/blocks/test_gmail.py` covering all email types and edge cases - **Added error handling and graceful fallbacks** for malformed data and missing dependencies #### Security & Performance: - **Recursion depth limiting** prevents infinite loops on malformed email structures - **Exception handling** ensures graceful degradation when API calls fail - **Efficient tree traversal** with early returns for better performance ### Checklist #### For code changes: - [x] I have clearly listed my changes in the PR description - [x] I have made a test plan - [x] I have tested my changes according to the test plan: <details> <summary>Test Plan</summary> - **Single-part text/plain emails** - Verified correct extraction of plain text content - **Multipart/alternative emails** - Tested preference for plain text over HTML when both available - **HTML-only emails** - Confirmed HTML to text conversion works correctly - **Nested multipart structures** - Tested deeply nested `multipart/mixed` containing `multipart/alternative` - **Attachment-based body content** - Verified downloading and decoding of body stored as attachments - **Base64 padding edge cases** - Tested malformed base64 data with missing padding - **Recursion depth limits** - Confirmed protection against infinite recursion - **Error handling scenarios** - Tested graceful fallbacks for API failures and missing dependencies - **Backward compatibility** - Ensured existing functionality remains unchanged for edge cases - **Integration testing** - Ran standalone verification script with 100% test pass rate </details> #### For configuration changes: - [x] `.env.example` is updated or already compatible with my changes - [x] `docker-compose.yml` is updated or already compatible with my changes - [x] I have included a list of my configuration changes in the PR description (under **Changes**) <details> <summary>Configuration Changes</summary> - Added `html2text` dependency to `pyproject.toml` - no environment or infrastructure changes required - No changes to ports, services, secrets, or databases - Fully backward compatible with existing Gmail API configuration </details> --------- Co-authored-by: Toran Bruce Richards <toran.richards@gmail.com> Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co> |