├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── llm_video_frames.py ├── pyproject.toml └── tests ├── test.mp4 └── test_video_frames.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | permissions: 8 | contents: read 9 | 10 | jobs: 11 | test: 12 | runs-on: ubuntu-latest 13 | strategy: 14 | matrix: 15 | python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"] 16 | steps: 17 | - uses: actions/checkout@v4 18 | - name: Install ffmpeg 19 | run: | 20 | sudo apt-get update 21 | sudo apt-get install -y ffmpeg 22 | - name: Set up Python ${{ matrix.python-version }} 23 | uses: actions/setup-python@v5 24 | with: 25 | python-version: ${{ matrix.python-version }} 26 | cache: pip 27 | cache-dependency-path: pyproject.toml 28 | - name: Install dependencies 29 | run: | 30 | pip install -e '.[test]' 31 | - name: Run tests 32 | run: | 33 | python -m pytest 34 | deploy: 35 | runs-on: ubuntu-latest 36 | needs: [test] 37 | environment: release 38 | permissions: 39 | id-token: write 40 | steps: 41 | - uses: actions/checkout@v4 42 | - name: Set up Python 43 | uses: actions/setup-python@v5 44 | with: 45 | python-version: "3.13" 46 | cache: pip 47 | cache-dependency-path: pyproject.toml 48 | - name: Install dependencies 49 | run: | 50 | pip install setuptools wheel build 51 | - name: Build 52 | run: | 53 | python -m build 54 | - name: Publish 55 | uses: pypa/gh-action-pypi-publish@release/v1 56 | -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push, pull_request] 4 | 5 | permissions: 6 | contents: read 7 | 8 | jobs: 9 | test: 10 | runs-on: ubuntu-latest 11 | strategy: 12 | matrix: 13 | python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"] 14 | steps: 15 | - uses: actions/checkout@v4 16 | - name: Install ffmpeg 17 | run: | 18 | sudo apt-get update 19 | sudo apt-get install -y ffmpeg 20 | - name: Set up Python ${{ matrix.python-version }} 21 | uses: actions/setup-python@v5 22 | with: 23 | python-version: ${{ matrix.python-version }} 24 | cache: pip 25 | cache-dependency-path: pyproject.toml 26 | - name: Install dependencies 27 | run: | 28 | pip install -e '.[test]' 29 | - name: Run tests 30 | run: | 31 | python -m pytest -vv 32 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | .vscode 11 | dist 12 | build 13 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # llm-video-frames 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/llm-video-frames.svg)](https://pypi.org/project/llm-video-frames/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/llm-video-frames?include_prereleases&label=changelog)](https://github.com/simonw/llm-video-frames/releases) 5 | [![Tests](https://github.com/simonw/llm-video-frames/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/llm-video-frames/actions/workflows/test.yml) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-video-frames/blob/main/LICENSE) 7 | 8 | LLM plugin to turn a video into individual frames 9 | 10 | ## Installation 11 | 12 | Install this plugin in the same environment as [LLM](https://llm.datasette.io/). 13 | ```bash 14 | llm install llm-video-frames 15 | ``` 16 | Requires `ffmpeg` installed and available on the system `PATH`. On macOS, you can install it using Homebrew: 17 | ```bash 18 | brew install ffmpeg 19 | ``` 20 | 21 | ## Usage 22 | 23 | The `llm-video-frames` plugin provides a [fragment loader](https://llm.datasette.io/en/stable/fragments.html#using-fragments-from-plugins) that extracts individual frames from a video file using `ffmpeg`. 24 | 25 | You can use the `video-frames:` fragment prefix to turn a video into a series of image attachments. 26 | 27 | ### Fragment syntax 28 | 29 | ``` 30 | video-frames:?fps=N×tamps=1 31 | ``` 32 | 33 | - ``: Path to the video file accessible to the environment where LLM runs. 34 | - `fps=N`: (optional) Number of frames per second to extract. Defaults to `1` if omitted. 35 | - `timestamps=1`: (optional) If set to `1`, overlays the filename and timestamp on each extracted frame in the bottom-right corner. 36 | 37 | ### Examples 38 | 39 | Extract 1 frame per second (default) from `video.mp4`: 40 | 41 | ```bash 42 | llm -f video-frames:video.mp4 'describe the key scenes in this video' 43 | ``` 44 | 45 | Extract 5 frames per second: 46 | 47 | ```bash 48 | llm -f 'video-frames:video.mp4?fps=5' 'summarize the video' 49 | ``` 50 | 51 | Extract 2 frames per second with filename and timestamps overlayed on frames: 52 | 53 | ```bash 54 | llm -f 'video-frames:video.mp4?fps=2×tamps=1' 'list notable events with timestamps' 55 | ``` 56 | 57 | ## Development 58 | 59 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 60 | ```bash 61 | cd llm-video-frames 62 | python -m venv venv 63 | source venv/bin/activate 64 | ``` 65 | Now install the dependencies and test dependencies: 66 | ```bash 67 | python -m pip install -e '.[test]' 68 | ``` 69 | To run the tests: 70 | ```bash 71 | python -m pytest 72 | ``` 73 | -------------------------------------------------------------------------------- /llm_video_frames.py: -------------------------------------------------------------------------------- 1 | import os 2 | import tempfile 3 | import subprocess 4 | import glob 5 | from urllib.parse import urlparse, parse_qs 6 | import llm 7 | 8 | 9 | @llm.hookimpl 10 | def register_fragment_loaders(register): 11 | register("video-frames", video_frames_loader) 12 | 13 | 14 | def video_frames_loader(argument: str): 15 | """ 16 | Fragment loader "video-frames:?fps=N×tamps=1" 17 | - extracts frames at `fps` per second (default 1) 18 | - if `timestamps=1`, overlays "filename hh:mm:ss" at bottom-right 19 | """ 20 | # parse out path and query params 21 | parts = urlparse(argument) 22 | video_path = parts.path 23 | params = parse_qs(parts.query) 24 | fps = int(params.get("fps", ["1"])[0]) 25 | timestamps = params.get("timestamps", ["0"])[0] in ("1", "true", "True") 26 | if not os.path.exists(video_path): 27 | raise ValueError(f"Video file not found: {video_path}") 28 | 29 | # prepare temp dir 30 | out_dir = tempfile.mkdtemp(prefix="llm_video_frames_") 31 | # base filename for overlay 32 | base_name = os.path.basename(video_path) 33 | 34 | # build ffmpeg filter 35 | vf_parts = [f"fps={fps}"] 36 | if timestamps: 37 | # overlay filename and timestamp (hh:mm:ss) at bottom-right 38 | timestamp_expr = r"%{pts\:hms}" # → %{pts\:hms} 39 | text = f"{base_name} {timestamp_expr}" # → "items.mov %{pts\:hms}" 40 | draw = ( 41 | "drawtext=fontcolor=white:fontsize=24:box=1:boxcolor=black@0.5" 42 | f":text='{text}':x=w-tw-10:y=h-th-10" 43 | ) 44 | vf_parts.append(draw) 45 | vf = ",".join(vf_parts) 46 | 47 | # output pattern 48 | pattern = os.path.join(out_dir, "frame_%05d.jpg") 49 | 50 | # run ffmpeg 51 | cmd = ["ffmpeg", "-v", "error", "-i", video_path, "-vf", vf, "-q:v", "2", pattern] 52 | try: 53 | subprocess.run(cmd, check=True) 54 | except subprocess.CalledProcessError as e: 55 | raise RuntimeError(f"ffmpeg failed: {e}") 56 | 57 | # collect frames 58 | files = sorted(glob.glob(os.path.join(out_dir, "frame_*.jpg"))) 59 | attachments = [llm.Attachment(path=f) for f in files] 60 | return attachments 61 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "llm-video-frames" 3 | version = "0.1" 4 | description = "LLM plugin to turn a video into individual frames" 5 | readme = "README.md" 6 | authors = [{name = "Simon Willison"}] 7 | license = "Apache-2.0" 8 | classifiers = [] 9 | requires-python = ">=3.9" 10 | dependencies = [ 11 | "llm>=0.25" 12 | ] 13 | 14 | [build-system] 15 | requires = ["setuptools"] 16 | build-backend = "setuptools.build_meta" 17 | 18 | [project.urls] 19 | Homepage = "https://github.com/simonw/llm-video-frames" 20 | Changelog = "https://github.com/simonw/llm-video-frames/releases" 21 | Issues = "https://github.com/simonw/llm-video-frames/issues" 22 | CI = "https://github.com/simonw/llm-video-frames/actions" 23 | 24 | [project.entry-points.llm] 25 | video_frames = "llm_video_frames" 26 | 27 | [project.optional-dependencies] 28 | test = ["pytest"] 29 | -------------------------------------------------------------------------------- /tests/test.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/simonw/llm-video-frames/daea91779ad42dd9e5df3ac67649285b6677f82c/tests/test.mp4 -------------------------------------------------------------------------------- /tests/test_video_frames.py: -------------------------------------------------------------------------------- 1 | import os 2 | import shutil 3 | import pytest 4 | 5 | # adjust this import path to wherever your loader code actually lives 6 | from llm_video_frames import video_frames_loader 7 | 8 | # skip entire module if ffmpeg is not installed 9 | ffmpeg_path = shutil.which("ffmpeg") 10 | if not ffmpeg_path: 11 | pytest.skip( 12 | "ffmpeg not found on PATH, skipping video frame extraction tests", 13 | allow_module_level=True, 14 | ) 15 | 16 | 17 | @pytest.fixture 18 | def video_file_path(tmp_path): 19 | """ 20 | Ensure there's a test.mp4 available. We expect a small 2-second mp4 21 | sitting next to this test file at tests/test.mp4; if not found, we skip. 22 | """ 23 | here = os.path.dirname(__file__) 24 | candidate = os.path.join(here, "test.mp4") 25 | if not os.path.exists(candidate): 26 | pytest.skip("test.mp4 not found in tests directory, skipping") 27 | return candidate 28 | 29 | 30 | def cleanup_attachments(attachments): 31 | """ 32 | Remove generated files and their parent temp directory. 33 | """ 34 | if not attachments: 35 | return 36 | # attachments are llm.Attachment objects with .path 37 | out_dir = os.path.dirname(attachments[0].path) 38 | shutil.rmtree(out_dir) 39 | 40 | 41 | def test_missing_file_raises_value_error(): 42 | fake = "/path/does/not/exist.mp4" 43 | with pytest.raises(ValueError) as exc: 44 | video_frames_loader(fake) 45 | assert "Video file not found" in str(exc.value) 46 | 47 | 48 | def test_default_fps_produces_two_frames(video_file_path): 49 | """ 50 | Default is fps=1 on a 2-second video -> 2 frames 51 | """ 52 | arg = f"video-frames:{video_file_path}" 53 | attachments = video_frames_loader(arg) 54 | try: 55 | paths = [a.path for a in attachments] 56 | assert len(paths) == 2, f"expected 2 frames, got {len(paths)}" 57 | for p in paths: 58 | assert os.path.exists(p), f"frame file missing: {p}" 59 | assert p.lower().endswith(".jpg") 60 | finally: 61 | cleanup_attachments(attachments) 62 | 63 | 64 | @pytest.mark.parametrize( 65 | "fps, expected_count", 66 | [ 67 | (1, 2), 68 | (2, 5), 69 | ], 70 | ) 71 | def test_fps_parameter_changes_frame_count(video_file_path, fps, expected_count): 72 | arg = f"video-frames:{video_file_path}?fps={fps}" 73 | attachments = video_frames_loader(arg) 74 | try: 75 | paths = [a.path for a in attachments] 76 | assert ( 77 | len(paths) == expected_count 78 | ), f"fps={fps} expected {expected_count} frames, got {len(paths)}" 79 | finally: 80 | cleanup_attachments(attachments) 81 | 82 | 83 | def test_timestamps_overlay_does_not_change_count(video_file_path): 84 | """ 85 | Turning on timestamps should not change the number of frames, just overlay text. 86 | """ 87 | arg = f"video-frames:{video_file_path}?timestamps=1" 88 | attachments = video_frames_loader(arg) 89 | try: 90 | paths = [a.path for a in attachments] 91 | # still 2 frames at default fps=1 92 | assert len(paths) == 2 93 | # basic sanity: files exist and are non‐empty 94 | for p in paths: 95 | assert os.path.getsize(p) > 0 96 | finally: 97 | cleanup_attachments(attachments) 98 | --------------------------------------------------------------------------------