[tools] refine wording, fix doc link and remove redundant codes (micr…

…osoft#159)

In this PR, there are 3 improvements:
- refine tools related workflow names.
- remove redundant codes.
- improve wording and fix doc link of READMEs.

.github/workflows/tools_release.yml → .github/workflows/tools_continuous_delivery.yml

@@ -1,4 +1,4 @@
-name: Promptflow Tools Release
+name: tools_continuous_delivery
 
 on:
   pull_request:
@@ -72,7 +72,7 @@ jobs:
 
   deploy_runtime_with_updated_tools_package:
     needs: continuous_delivery_release
-    uses: ./.github/workflows/deploy_runtime.yml
+    uses: ./.github/workflows/tools_deploy_runtime.yml
     name: Deploy runtime
     with:
       ToolsPackageVersion: ${{ needs.continuous_delivery_release.outputs.PackageVersion }}

.github/workflows/deploy_runtime.yml → .github/workflows/tools_deploy_runtime.yml

@@ -1,4 +1,4 @@
-name: Deploy runtime
+name: tools_deploy_runtime
 
 on:
   workflow_call:

.github/workflows/tools_release_tag.yml

@@ -1,4 +1,4 @@
-name: Promptflow Tools Release Tag
+name: create_tools_release_tag
 on:
   workflow_dispatch:
     inputs:

.github/workflows/tools_secret_upload.yml

@@ -1,4 +1,4 @@
-name: Promptflow Tools Secrets Upload
+name: tools_secret_upload
 # Triggers the workflow manually
 on:
   workflow_dispatch:

.github/workflows/tools_tests.yml

@@ -1,4 +1,4 @@
-name: Promptflow Tools Test
+name: tools_tests
 on:
   # Triggers the workflow pull request events but only for the main branch
   pull_request:

src/promptflow-tools/README.dev.md

@@ -1,4 +1,4 @@
-# Development Guide for Promptflow builtin tools
+# Development Guide
 
 ## Prerequisites
 
@@ -10,10 +10,10 @@ pip install pytest pytest-mock
 ## Run tests locally
 
 - Create connection config file by `cp connections.json.example connections.json`.
-- Fill in the keys and secrets manually in `connections.json`.
+- Fill in fields manually in `connections.json`.
 - `cd tests` and run `pytest -s -v` to run all tests.
 
 ## Run tests in CI
 
-Use this [workflow](https://github.com/microsoft/promptflow/actions/workflows/tools_secret_upload.yml) to upload secrets in key vault. The secrets you uploaded would be used in [Promptflow Tools Test CI](https://github.com/microsoft/promptflow/actions/workflows/tools_tests.yml). Note that you only need to upload the SECRETS.
-  > [!NOTE] After triggering the flow, kindly request approval from Promptflow Support before proceeding further.
+Use this [workflow](https://github.com/microsoft/promptflow/actions/workflows/tools_secret_upload.yml) to upload secrets in key vault. The secrets you uploaded would be used in [tools tests](https://github.com/microsoft/promptflow/actions/workflows/tools_tests.yml). Note that you only need to upload the SECRETS.
+  > [!NOTE] After triggering the workflow, kindly request approval from Promptflow Support before proceeding further.

src/promptflow-tools/README.md

@@ -1,10 +1,10 @@
-# Promptflow tools
+# Prompt Flow Tools
 
 [![Python package](https://img.shields.io/pypi/v/promptflow-tools)](https://pypi.org/project/promptflow-tools/)
-[![license: MIT](https://img.shields.io/badge/License-MIT-purple.svg)](../LICENSE)
+[![License: MIT](https://img.shields.io/github/license/microsoft/promptflow)](https://github.com/microsoft/promptflow/blob/main/LICENSE)
 
 ## 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 for developers.
+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 support users to create their own tools and share them with others. See [Custom tool package creation and usage](https://github.com/Azure/promptflow/blob/main/docs/how-to-guides/how-to-create-and-use-your-own-tool-package.md) for more details.
+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 [Custom tool package creation and usage](https://github.com/microsoft/promptflow/blob/main/docs/how-to-guides/how-to-create-and-use-your-own-tool-package.md) for more details.

src/promptflow-tools/promptflow/tools/common.py

@@ -1,13 +1,9 @@
 import functools
-import http
 import json
 import re
-import socket
 import sys
 import time
 
-import requests
-import urllib3
 from jinja2 import Template
 from openai.error import APIError, OpenAIError, RateLimitError, ServiceUnavailableError, Timeout, APIConnectionError
 from promptflow.exceptions import SystemErrorException, UserErrorException
@@ -121,23 +117,6 @@ def parse_chat(chat_str):
     return chat_list
 
 
-# Define the retriable exceptions
-retriable_exceptions = (
-    urllib3.exceptions.HTTPError,  # this is a parent class, we might not list its sub-class
-    urllib3.exceptions.MaxRetryError,
-    urllib3.exceptions.TimeoutError,
-    urllib3.exceptions.ConnectionError,
-    socket.timeout,
-    http.client.RemoteDisconnected,
-    http.client.HTTPException,
-    requests.exceptions.ConnectionError,
-    requests.exceptions.Timeout,
-    requests.exceptions.RetryError,
-    requests.exceptions.TooManyRedirects,
-    requests.exceptions.HTTPError,
-)
-
-
 def handle_openai_error(tries: int = 10, delay: float = 8.0):
     """
     A decorator function that used to handle OpenAI error.

src/promptflow-tools/promptflow/tools/exception.py

@@ -34,7 +34,7 @@ def to_openai_error_message(e: Exception) -> str:
 
 
 class WrappedOpenAIError(UserErrorException):
-    """Base exception raised when call openai api."""
+    """Refine error messages on top of native openai errors."""
 
     def __init__(self, ex: OpenAIError, **kwargs):
         super().__init__(target=ErrorTarget.TOOL, **kwargs)

src/promptflow-tools/setup.py

@@ -23,7 +23,7 @@
 setup(
     name=PACKAGE_NAME,
     version=version,
-    description="Prompt Flow Tools",
+    description="Builtin tools of prompt flow",
     author="Microsoft Corporation",
     classifiers=[
         "Programming Language :: Python :: 3",