Prompt flow tools
Introduction
Tools are the fundamental building blocks of a flow in Azure Machine Learning prompt flow. Each tool is a simple, executable unit with a specific function, allowing users to perform various tasks. By combining different tools, users can create a flow that accomplishes a wide range of goals. One of the key benefit of prompt flow tools is their seamless integration with third-party APIs and python open source packages. This not only improves the functionality of large language models but also makes the development process more efficient.
In this package, we provide a set of builtin tools of prompt flow, which are the most commonly used tools in the development of AI applications. We also provide a flexible way for users to create their own tools and share them with others. See Create and Use Tool Package for more details.
Release History
1.6.1 (2025.6.10)
- Fixed a bug that could allow for arbitrary code execution when parsing
tool_calls - Fixed a bug that could allow prompt injection
1.6.0 (2025.02.19)
Bug fixed
- Fix for jinja2 template rendering.
1.5.0 (2025.01.29)
Features Added
- Add "detail" to "Azure OpenAI GPT-4 Turbo with Vision" and "OpenAI GPT-4V" tool inputs.
- Avoid unintended parsing by role process to user flow inputs in prompt templates.
- Introduce universal contract LLM tool and combine "Azure OpenAI GPT-4 Turbo with Vision" and "OpenAI GPT-4V" tools to "LLM-Vision" tool.
Improvements
- Dropped Python 3.8 support for security reasons.
1.4.0 (2024.03.26)
Features Added
- Enable token based auth in azure openai connection for tools.
- Add "seed" to LLM and GPT-Vision tool inputs.
Improvements
- Improve error message when LLM tool meets gpt-4-vision-preview model.
Bugs Fixed
- Set default values to workspace triad parameters of dynamic list function to avoid misleading errors when clicking tool input.
1.3.0 (2024.03.01)
Improvements
- Disable openai built-in retry mechanism for better debuggability and real-time status updates.
- Refine the retry-after interval for openai retry error.
1.2.0 (2024.02.07)
Features Added
- Support tool "Azure OpenAI GPT-4 Turbo with Vision" to auto list "deployment_name".
Improvements
- Match the promptflow-tools setup to promptflow setup.
1.1.0 (2024.01.23)
Features Added
- Use ruamel.yaml instead of pyyaml in promptflow.
1.0.3 (2024.01.08)
Features Added
- Add new tool "Azure OpenAI GPT-4 Turbo with Vision".
- Support "response_format" for azure openai chat api in LLM tool.
1.0.1 (2023.12.13)
Features Added
- Support "response_format" for openai chat api in LLM tool.
- Add "allow_manual_entry" for embedding tool.
Improvements
- Handle all OpenSource\HuggingFace Models with the same MIR request format in 'Open Model LLM' tool.
1.0.0 (2023.11.30)
Features Added
- Support openai 1.x in promptflow-tools.
- Add new tool "OpenAI GPT-4V".
Metadata
Release files for promptflow-tools 1.6.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| promptflow_tools-1.6.1-py3-none-any.whl | Python 3 | none | any | Details |
Release files / promptflow_tools-1.6.1-py3-none-any.whl
| Download URL | promptflow_tools-1.6.1-py3-none-any.whl |
|---|---|
| Size | 54.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4131a68ab156bef083e35b71e55c7a9cb2462bc26a9d3f05edd07238113ee477
|
|
BLAKE2b-256 checksum How to use checksums |
8f5af8154f8faa2c6a16043684b0e44c4b47384e872d0ebb02064a47056aa77b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.9.21
|
Security for promptflow-tools 1.6.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.