Name | promptfold JSON |
Version |
1.0.15
JSON |
| download |
home_page | None |
Summary | Python client for PromptFold API - optimize prompts with PromptFold |
upload_time | 2025-08-07 18:51:44 |
maintainer | None |
docs_url | None |
author | None |
requires_python | >=3.8 |
license | MIT |
keywords |
promptfold
optimization
api
client
|
VCS |
 |
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# PromptFold Client Library
This package provides a simple Python client for the PromptFold API available on PyPI.
## Installation
```bash
pip install promptfold
```
## Usage
```python
import openai
from promptfold_client import PromptFold
# Initialize PromptFold client, compress your system prompt
pf_client = PromptFold(api_key="YOUR_PROMPTFOLD_API_KEY", system_prompt="Your system prompt.")
# Compress the original user prompt and system prompt
compressed = pf_client.compress_prompt(user_prompt="Input user prompt")
# Call OpenAI's GPT-4 with the compressed prompt
openai.api_key = "YOUR_OPENAI_API_KEY"
response = openai.ChatCompletion.create(
model="gpt-4o",
messages=[
{"role": "system", "content": compressed.compressed_system_prompt},
{"role": "user", "content": compressed.compressed_user_prompt}
]
)
# Print the response from GPT-4
print(response["choices"][0]["message"]["content"])
```
## Publishing a New Version (for Maintainers)
Publishing the client is handled by a script that automates the entire process.
**Prerequisites:**
1. **PyPI Account:** You need an account on [PyPI](https://pypi.org) and an API token.
2. **Twine Configuration:** Your local machine must be configured to authenticate with PyPI. You can do this by setting the `TWINE_USERNAME` and `TWINE_PASSWORD` environment variables.
**To publish a new version:**
1. Navigate to the client directory: `cd promptfold_client`
2. Run the publishing script. You have two options:
* **To automatically bump the patch version** (e.g., `1.0.1` -> `1.0.2`), run the script without arguments:
```bash
./publish_pypi.sh
```
* **To specify an exact version** (e.g., for a major release like `2.0.0`), provide it as an argument:
```bash
./publish_pypi.sh 2.0.0
```
3. The script will handle everything else automatically.
Raw data
{
"_id": null,
"home_page": null,
"name": "promptfold",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "promptfold, optimization, api, client",
"author": null,
"author_email": "PromptFold Team <team@promptfold.com>",
"download_url": "https://files.pythonhosted.org/packages/cd/3c/24ecc4de65d8678633130bfba5f6ebe572a7c5fc15948f218873fbfdb2ff/promptfold-1.0.15.tar.gz",
"platform": null,
"description": "# PromptFold Client Library\n\nThis package provides a simple Python client for the PromptFold API available on PyPI.\n\n## Installation\n```bash\npip install promptfold\n```\n\n## Usage\n\n```python\nimport openai\nfrom promptfold_client import PromptFold\n\n# Initialize PromptFold client, compress your system prompt\npf_client = PromptFold(api_key=\"YOUR_PROMPTFOLD_API_KEY\", system_prompt=\"Your system prompt.\")\n\n# Compress the original user prompt and system prompt\ncompressed = pf_client.compress_prompt(user_prompt=\"Input user prompt\")\n\n# Call OpenAI's GPT-4 with the compressed prompt\nopenai.api_key = \"YOUR_OPENAI_API_KEY\"\nresponse = openai.ChatCompletion.create(\n model=\"gpt-4o\",\n messages=[\n {\"role\": \"system\", \"content\": compressed.compressed_system_prompt},\n {\"role\": \"user\", \"content\": compressed.compressed_user_prompt}\n ]\n)\n\n# Print the response from GPT-4\nprint(response[\"choices\"][0][\"message\"][\"content\"])\n\n```\n\n## Publishing a New Version (for Maintainers)\n\nPublishing the client is handled by a script that automates the entire process.\n\n**Prerequisites:**\n1. **PyPI Account:** You need an account on [PyPI](https://pypi.org) and an API token.\n2. **Twine Configuration:** Your local machine must be configured to authenticate with PyPI. You can do this by setting the `TWINE_USERNAME` and `TWINE_PASSWORD` environment variables.\n\n**To publish a new version:**\n1. Navigate to the client directory: `cd promptfold_client`\n2. Run the publishing script. You have two options:\n * **To automatically bump the patch version** (e.g., `1.0.1` -> `1.0.2`), run the script without arguments:\n ```bash\n ./publish_pypi.sh\n ```\n * **To specify an exact version** (e.g., for a major release like `2.0.0`), provide it as an argument:\n ```bash\n ./publish_pypi.sh 2.0.0\n ```\n3. The script will handle everything else automatically.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Python client for PromptFold API - optimize prompts with PromptFold",
"version": "1.0.15",
"project_urls": {
"Homepage": "https://github.com/paulcrowley/promptfold",
"Issues": "https://github.com/paulcrowley/promptfold/issues",
"Repository": "https://github.com/paulcrowley/promptfold"
},
"split_keywords": [
"promptfold",
" optimization",
" api",
" client"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "aa4f5f0da6d4d086df90c5fa41e5a387f9ab4eb9e4abcaea02210c3298187567",
"md5": "798f86169650f76da37b0d04a2dc31f8",
"sha256": "23203ced19c2fa362643207cfb181e7e5dd24e3c70309b3514ce93c7ad7f7520"
},
"downloads": -1,
"filename": "promptfold-1.0.15-py3-none-any.whl",
"has_sig": false,
"md5_digest": "798f86169650f76da37b0d04a2dc31f8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 4997,
"upload_time": "2025-08-07T18:51:43",
"upload_time_iso_8601": "2025-08-07T18:51:43.470686Z",
"url": "https://files.pythonhosted.org/packages/aa/4f/5f0da6d4d086df90c5fa41e5a387f9ab4eb9e4abcaea02210c3298187567/promptfold-1.0.15-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "cd3c24ecc4de65d8678633130bfba5f6ebe572a7c5fc15948f218873fbfdb2ff",
"md5": "d8be89445fb6bdae039fd513e38bb188",
"sha256": "b7c7c9b536a3e99619bdff9edf83410fbdbfa35c548eda924f5728f875e4f91d"
},
"downloads": -1,
"filename": "promptfold-1.0.15.tar.gz",
"has_sig": false,
"md5_digest": "d8be89445fb6bdae039fd513e38bb188",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 4939,
"upload_time": "2025-08-07T18:51:44",
"upload_time_iso_8601": "2025-08-07T18:51:44.633988Z",
"url": "https://files.pythonhosted.org/packages/cd/3c/24ecc4de65d8678633130bfba5f6ebe572a7c5fc15948f218873fbfdb2ff/promptfold-1.0.15.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-07 18:51:44",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "paulcrowley",
"github_project": "promptfold",
"github_not_found": true,
"lcname": "promptfold"
}