Compare commits

..

2 Commits

Author SHA1 Message Date
Clelia (Astra) Bertelli 8bdb1c5594 chore: correct title 2025-07-31 11:13:38 +02:00
Clelia (Astra) Bertelli 8ed543ba67 feat: add ts examples (clean) 2025-07-30 20:14:28 +02:00
184 changed files with 5295 additions and 6221 deletions
-8
View File
@@ -1,8 +0,0 @@
# Changesets
Hello and welcome! This folder has been automatically generated by `@changesets/cli`, a build tool that works
with multi-package repos, or single-package repos to help you version and publish your code. You can
find the full documentation for it [in our repository](https://github.com/changesets/changesets)
We have a quick list of common questions to get you started engaging with this project in
[our documentation](https://github.com/changesets/changesets/blob/main/docs/common-questions.md)
-11
View File
@@ -1,11 +0,0 @@
{
"$schema": "https://unpkg.com/@changesets/config@3.1.1/schema.json",
"changelog": "@changesets/cli/changelog",
"commit": false,
"fixed": [],
"linked": [],
"access": "restricted",
"baseBranch": "main",
"updateInternalDependencies": "patch",
"ignore": []
}
+1 -4
View File
@@ -6,11 +6,8 @@ on:
push:
branches:
- main
paths:
- "py/**"
pull_request:
paths:
- "py/**"
env:
UV_VERSION: "0.7.20"
+1 -9
View File
@@ -1,13 +1,5 @@
name: Build Package - TypeScript
on:
push:
branches:
- main
paths:
- "ts/**"
pull_request:
paths:
- "ts/**"
on: [pull_request]
jobs:
pre_release:
-95
View File
@@ -1,95 +0,0 @@
name: Claude Code
on:
issue_comment:
types: [created]
pull_request_review_comment:
types: [created]
issues:
types: [opened, assigned]
pull_request_review:
types: [submitted]
jobs:
claude:
if: |
(github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
(github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
issues: read
id-token: write
steps:
- name: Check repository access
id: check-access
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
# Get the user who triggered the event
case "${{ github.event_name }}" in
"issue_comment")
USER="${{ github.event.comment.user.login }}"
;;
"pull_request_review_comment")
USER="${{ github.event.comment.user.login }}"
;;
"pull_request_review")
USER="${{ github.event.review.user.login }}"
;;
"issues")
USER="${{ github.event.issue.user.login }}"
;;
esac
echo "Checking repository access for user: $USER"
# Check if user has write access to the repository
REPO="${{ github.repository }}"
if gh api repos/$REPO/collaborators/$USER/permission --jq '.permission' | grep -E "(admin|write)" > /dev/null 2>&1; then
echo "User $USER has write access to the repository"
echo "authorized=true" >> $GITHUB_OUTPUT
else
echo "User $USER does not have write access to the repository"
echo "authorized=false" >> $GITHUB_OUTPUT
exit 1
fi
- name: Checkout repository
if: steps.check-access.outputs.authorized == 'true'
uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Run Claude Code
if: steps.check-access.outputs.authorized == 'true'
id: claude
uses: anthropics/claude-code-action@beta
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_GITHUB_API_KEY }}
# Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
# model: "claude-opus-4-20250514"
# Optional: Customize the trigger phrase (default: @claude)
# trigger_phrase: "/claude"
# Optional: Trigger when specific user is assigned to an issue
# assignee_trigger: "claude-bot"
# Optional: Allow Claude to run specific commands
# Allow bash commands to be run, for things like running tests, linting, etc.
allowed_tools: "Bash(rg:*),Bash(find:*),Bash(grep:*),Bash(pnpm:*),Bash(npm:*),Bash(uv:*),Bash(pip:*),Bash(pipx:*),Bash(make:*),Bash(cd:*),WebFetch"
# Optional: Add custom instructions for Claude to customize its behavior for your project
# custom_instructions: |
# Follow our coding standards
# Ensure all new code has tests
# Use TypeScript for new files
# Optional: Custom environment variables for Claude
# claude_env: |
# NODE_ENV: test
+3 -4
View File
@@ -4,11 +4,9 @@ on:
push:
branches:
- main
paths:
- "ts/**"
pull_request:
paths:
- "ts/**"
branches:
- main
env:
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
@@ -28,6 +26,7 @@ jobs:
with:
node-version-file: "ts/llama_cloud_services/.nvmrc"
- name: Install dependencies
working-directory: ts/llama_cloud_services/
run: pnpm install --no-frozen-lockfile
- name: Run lint
working-directory: ts/llama_cloud_services/
-52
View File
@@ -1,52 +0,0 @@
name: Publish - Changeset
on:
push:
branches: [main]
concurrency: ${{ github.workflow }}-${{ github.ref }}
jobs:
publish:
name: Publish
runs-on: ubuntu-latest
# Only run if this is a merge commit and the PR was authored by github-actions[bot]
if: ${{ github.event.head_commit.message != null && startsWith(github.event.head_commit.message, 'Merge pull request') && contains(github.event.head_commit.message, '/changeset-release/main') }}
steps:
- name: Checkout Repo
uses: actions/checkout@v4
- uses: pnpm/action-setup@v3
with:
version: 10
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install uv
uses: astral-sh/setup-uv@v3
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: "ts/llama_cloud_services/.nvmrc"
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Add auth token to .npmrc file
run: |
cat << EOF >> ".npmrc"
//registry.npmjs.org/:_authToken=$NPM_TOKEN
EOF
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
- name: Publish packages based on changesets
run: |
pnpm run release
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
PYPI_TOKEN: ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
+1 -16
View File
@@ -22,29 +22,14 @@ jobs:
node-version-file: "ts/llama_cloud_services/.nvmrc"
- name: Install dependencies
working-directory: ts/llama_cloud_services
run: pnpm install --no-frozen-lockfile
- name: Run Build
working-directory: ts/llama_cloud_services/
run: pnpm build
- name: Build tarball
run: |
pnpm pack
working-directory: ts/llama_cloud_services
- name: Setup npm authentication
run: echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" > ~/.npmrc
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
- name: Release
working-directory: ts/llama_cloud_services
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
run: pnpm publish --access public --no-git-checks
- name: Create release
uses: ncipollo/release-action@v1
with:
-38
View File
@@ -1,38 +0,0 @@
name: Test end-to-end - Python
on:
pull_request:
paths:
- "py/**"
env:
UV_VERSION: "0.7.20"
LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
jobs:
test_e2e:
runs-on: ubuntu-latest
strategy:
# You can use PyPy versions in python-version.
# For example, pypy-2.7 and pypy-3.8
matrix:
python-version: ["3.12"]
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Install uv
uses: astral-sh/setup-uv@v6
with:
version: ${{ env.UV_VERSION }}
- name: Set up Python
run: uv python install ${{ matrix.python-version }} && uv python pin ${{ matrix.python-version }}
- name: Run Tests
working-directory: py
run: uv run pytest unit_tests/ tests/ -v
- name: Remove virtual environment
working-directory: py
run: rm -rf .venv/
+2 -5
View File
@@ -4,14 +4,11 @@ on:
push:
branches:
- main
paths:
- "py/**"
pull_request:
paths:
- "py/**"
env:
UV_VERSION: "0.7.20"
LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
jobs:
test:
@@ -35,7 +32,7 @@ jobs:
- name: Run Tests
working-directory: py
run: uv run pytest unit_tests/ -v
run: uv run -- pytest tests/**/test_*.py
- name: Remove virtual environment
working-directory: py
+6 -14
View File
@@ -4,11 +4,9 @@ on:
push:
branches:
- main
paths:
- "ts/**"
pull_request:
paths:
- "ts/**"
branches:
- main
env:
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
@@ -17,8 +15,7 @@ env:
LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
jobs:
test:
name: Test - TypeScript
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -30,13 +27,8 @@ jobs:
with:
node-version-file: "ts/llama_cloud_services/.nvmrc"
- name: Install dependencies
working-directory: ts/llama_cloud_services/
run: pnpm install --no-frozen-lockfile
- name: Run Build
- name: Run tests
working-directory: ts/llama_cloud_services/
run: pnpm build
- name: Run Tests
working-directory: ts/llama_cloud_services/
run: pnpm test
- name: Run e2e tests
working-directory: ts/e2e-tests/
run: pnpm test
run: pnpm test --run
-47
View File
@@ -1,47 +0,0 @@
name: Version Bump - Changeset
on:
push:
branches:
- main
concurrency: ${{ github.workflow }}-${{ github.ref }}
jobs:
version:
name: Version Bump
runs-on: ubuntu-latest
steps:
- name: Checkout Repo
uses: actions/checkout@v4
with:
# Need to fetch full history for changesets
fetch-depth: 0
- uses: pnpm/action-setup@v3
with:
version: 10
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install uv
uses: astral-sh/setup-uv@v3
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: "ts/cute_cats_terminal/.nvmrc"
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Create Release Pull Request
id: changesets
uses: changesets/action@v1
with:
version: pnpm run version
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+4 -5
View File
@@ -15,7 +15,6 @@ repos:
- id: end-of-file-fixer
- id: mixed-line-ending
- id: trailing-whitespace
exclude: ^ts/llama_cloud_services/src/client/
- repo: https://github.com/charliermarsh/ruff-pre-commit
rev: v0.1.5
@@ -34,7 +33,7 @@ repos:
rev: v1.0.1
hooks:
- id: mypy
exclude: ^py/tests|^py/unit_tests
exclude: ^py/tests/
additional_dependencies:
[
"types-requests",
@@ -64,13 +63,13 @@ repos:
rev: v3.0.3
hooks:
- id: prettier
exclude: ^(uv.lock|ts/llama_cloud_services/pnpm-lock.yaml|ts/e2e-tests)
exclude: uv.lock
- repo: https://github.com/codespell-project/codespell
rev: v2.2.6
hooks:
- id: codespell
additional_dependencies: [tomli]
exclude: ^(uv.lock|docs|ts|examples|pnpm-lock.yaml)
exclude: ^(uv.lock|docs|ts)
args:
[
"--ignore-words-list",
@@ -87,4 +86,4 @@ repos:
- id: toml-sort-fix
exclude: ".*uv.lock"
exclude: ^(.github/ISSUE_TEMPLATE|ts/llama_cloud_services/src/client|pnpm-lock.yaml)
exclude: .github/ISSUE_TEMPLATE
+18 -151
View File
@@ -1,166 +1,33 @@
# Contribute to `llama-cloud-services`
# Python
## Common Patterns
## Installation
### Issues
This project uses uv. Create a virtual environment, and run `uv sync`
One of the forms of contribution can be issues.
## Versioning (Maintainers only)
Issues should be used when there are bugs or feature request you would like to bring to the attention of the maintainers.
Before merging your changes, make sure to bump the versions.
When opening an issue:
Make a version bump to `pyproject.toml`. If the underlying dependency on the llamacloud platform OpenAPI
sdk needs bumping, make sure to bring that in as well. If updating dependencies, run `uv lock`.
- preferably, use the provided templates
- check for other issues (closed and open) to avoid duplicates
- try to be detailed and specific, reporting all the pieces the maintainer would need to have in order to reproduce your issue.
The legacy `llama_parse` package re-exports some of `llama_cloud_services` in the old namespace. The
versions need to be kept consistent to sidecar it with `llama_cloud_services`. Bump it's version in `llama_parse/pyproject.toml`, and also bump it's dependency version of `llama-cloud-services` to match.
### Pull requests
**Note**: Don't worry about updating the `llama_parse/poetry.lock` file when bumping versions. The GitHub action will automatically run `poetry lock` for the llama_parse package during the build process (though it doesn't commit the updated lockfile back to the repo).
In order to open a valid pull request:
You can also do this with `./scripts/version-bump.py set 0.x.x` if you have `uv` installed.
- Fork the repository
- Checkout a secondary branch (common prefixes for secondary branches include: `fix`, `feat`, `chore`, `docs`). We tend to prefer the naming convention that uses `/`, such as: `fix/your-awesome-bug-fix`.
- Add and commit the changes to the secondary branch, following language-specific logic (see below)
- When the changes are pushed to your branch, open a pull request
Once the change is merged, push a tag `git tag -a v0.x.x -m 0.x.x` and `git push origin 0.x.x`.
## Python
This tagging step can be done with `./scripts/version-bump tag`.
### Set Up
# Typescript
The two python packages, which can be found under `py/`, are:
## Installation
- `llama-cloud-services`
- `llama-parse`
...
> [!NOTE]
>
> `llama-parse` mostly re-exports from `llama-cloud-services`, so you should not modify that directly.
## Versioning
These packages are managed through [uv](https://docs.astral.sh/uv/), so make sure to have uv [installed](https://docs.astral.sh/uv/getting-started/installation/).
### Tests
It is important to make sure all tests pass after your changes, and cover new features with suitable unit tests.
Tests are found in `py/tests/` (end to end) and `py/unit_tests/` (unit tests, no API key required) and you can execute them with:
```bash
pytest tests/ unit_tests/
```
### Pre-Commit Versioning
Once you made your changes and tested them, **prior to committing** you should run (from the root folder) this command to automatically bump the version of python packages:
```bash
pnpm pre-commit-version
```
this will prompt you to choose what package's version you want to bump and what kind of bump you want to perform. Choose `@llama_cloud_services/py` for python and choose the version bump according to the type of changing you made.
### Pre-commit checks
Before you commit, your files should pass the linting and formatting requirements. In order to do that, you should have `pre-commit` installed and set-up in your repository:
```bash
pip install pre-commit
pre-commit install
```
Once you have that set up, the files will be automatically linted and formatted according to the requirements.
## TypeScript
### Set Up
The TypeScript package, which can be found under `ts/llama_cloud_services/`, is managed through [`pnpm`](https://pnpm.io), so make sure to have it [installed](https://pnpm.io/installation).
In order to be able to run and test the package, make sure to install all the dependencies:
```bash
pnpm install
```
### Activate Test Mode
In order to activate test mode (to dynamically test your changes while you are performing them) you can use:
```bash
pnpm turbo run dev
```
### Test
It is important to make sure all tests pass after your changes, and cover new features with suitable unit tests.
Tests are found in `ts/llama_cloud_services/tests/` and you can execute them with:
```bash
pnpm test
```
### Pre-Commit Versioning
Once you made your changes and tested them, **prior to committing** you should run (from the root folder) two commands to automatically bump the version of python packages:
```bash
pnpm pre-commit-version
```
This will prompt you to choose what package's version you want to bump and what kind of bump you want to perform. Choose `llama-cloud-services` for TypeScript and choose the version bump according to the type of changing you made.
### Pre-commit checks
Before you commit, your files should pass the linting and formatting requirements. In order to do that, run (from the root folder):
```bash
pnpm pre-commit
```
The files will be then automatically linted and formatted according to the requirements.
## TypeScript _and_ Python
If you change **both PY and TS**, for versioning run:
```bash
pnpm pre-commit-version # choose both packages
```
## Release (maintainers only)
Every push to main might trigger a release.
Whether a release is pushed out or not depends on the presence of versioning files in `.changesets`: if you want a release to be packaged, then, you need to always run `pnpm pre-commit-version` prior to merging a pull request into main. See [version_bump_and_release](./.github/workflows/version_bump_and_release.yml) action to better understand the process.
You can, nevertheless, manually set up language-specific releases, using the logic reported below.
### Python
To release `llama-cloud-services` and `llama-parse` in Python, run:
```bash
git checkout main
git pull
git tag <your-version> # e.g. v0.7.0
git push <your-version>
```
> [!NOTE]
>
> The tag must start with `v`
This will trigger the release workflow automatically.
### TypeScript
To release `llama-cloud-services` in TypeScript, run:
```bash
git checkout main
git pull
git tag llama-cloud-services@<your-version> # e.g. llama-cloud-services@0.3.0
git push origin llama-cloud-services@<your-version>
```
This will trigger the release workflow automatically.
...
+9
View File
@@ -0,0 +1,9 @@
# LlamaCloud Services Examples - Python
In this folder you will find several python notebooks with examples regarding:
- [LlamaParse](./parse/)
- [LlamaExtract](./extract/)
- [LlamaReport](./report/)
Follow the instructions of each notebook to get started!

Before

Width:  |  Height:  |  Size: 3.3 MiB

After

Width:  |  Height:  |  Size: 3.3 MiB

Before

Width:  |  Height:  |  Size: 67 KiB

After

Width:  |  Height:  |  Size: 67 KiB

Before

Width:  |  Height:  |  Size: 202 KiB

After

Width:  |  Height:  |  Size: 202 KiB

Before

Width:  |  Height:  |  Size: 440 KiB

After

Width:  |  Height:  |  Size: 440 KiB

Before

Width:  |  Height:  |  Size: 156 KiB

After

Width:  |  Height:  |  Size: 156 KiB

Before

Width:  |  Height:  |  Size: 85 KiB

After

Width:  |  Height:  |  Size: 85 KiB

Before

Width:  |  Height:  |  Size: 893 KiB

After

Width:  |  Height:  |  Size: 893 KiB

Before

Width:  |  Height:  |  Size: 6.9 MiB

After

Width:  |  Height:  |  Size: 6.9 MiB

Before

Width:  |  Height:  |  Size: 195 KiB

After

Width:  |  Height:  |  Size: 195 KiB

Before

Width:  |  Height:  |  Size: 363 KiB

After

Width:  |  Height:  |  Size: 363 KiB

Before

Width:  |  Height:  |  Size: 343 KiB

After

Width:  |  Height:  |  Size: 343 KiB

Before

Width:  |  Height:  |  Size: 185 KiB

After

Width:  |  Height:  |  Size: 185 KiB

Before

Width:  |  Height:  |  Size: 254 KiB

After

Width:  |  Height:  |  Size: 254 KiB

Before

Width:  |  Height:  |  Size: 650 KiB

After

Width:  |  Height:  |  Size: 650 KiB

Before

Width:  |  Height:  |  Size: 72 KiB

After

Width:  |  Height:  |  Size: 72 KiB

Before

Width:  |  Height:  |  Size: 88 KiB

After

Width:  |  Height:  |  Size: 88 KiB

Before

Width:  |  Height:  |  Size: 200 KiB

After

Width:  |  Height:  |  Size: 200 KiB

Before

Width:  |  Height:  |  Size: 115 KiB

After

Width:  |  Height:  |  Size: 115 KiB

Before

Width:  |  Height:  |  Size: 334 KiB

After

Width:  |  Height:  |  Size: 334 KiB

Before

Width:  |  Height:  |  Size: 202 KiB

After

Width:  |  Height:  |  Size: 202 KiB

Before

Width:  |  Height:  |  Size: 1.2 MiB

After

Width:  |  Height:  |  Size: 1.2 MiB

Before

Width:  |  Height:  |  Size: 170 KiB

After

Width:  |  Height:  |  Size: 170 KiB

Before

Width:  |  Height:  |  Size: 580 KiB

After

Width:  |  Height:  |  Size: 580 KiB

Before

Width:  |  Height:  |  Size: 271 KiB

After

Width:  |  Height:  |  Size: 271 KiB

Before

Width:  |  Height:  |  Size: 1.5 MiB

After

Width:  |  Height:  |  Size: 1.5 MiB

Before

Width:  |  Height:  |  Size: 350 KiB

After

Width:  |  Height:  |  Size: 350 KiB

Before

Width:  |  Height:  |  Size: 47 KiB

After

Width:  |  Height:  |  Size: 47 KiB

Before

Width:  |  Height:  |  Size: 344 KiB

After

Width:  |  Height:  |  Size: 344 KiB

@@ -147,7 +147,7 @@
"documents = []\n",
"\n",
"for i, page in enumerate(pages):\n",
" # loop through items of the page\n",
" # loop trough items of the page\n",
" for item in page[\"items\"]:\n",
" document = Document(\n",
" text=item[\"md\"], extra_info={\"bbox\": item[\"bBox\"], \"page\": i}\n",

Before

Width:  |  Height:  |  Size: 2.3 MiB

After

Width:  |  Height:  |  Size: 2.3 MiB

Some files were not shown because too many files have changed in this diff Show More