transformers/tests/tools/test_python_interpreter.py
Sylvain Gugger 3335724376
Test composition (#23214)
* Remove nestedness in tool config

* Really do it

* Use remote tools descriptions

* Work

* Clean up eval

* Changes

* Tools

* Tools

* tool

* Fix everything

* Use last result/assign for evaluation

* Prompt

* Remove hardcoded selection

* Evaluation for chat agents

* correct some spelling

* Small fixes

* Change summarization model (#23172)

* Fix link displayed

* Update description of the tool

* Fixes in chat prompt

* Custom tools, custom prompt

* Tool clean up

* save_pretrained and push_to_hub for tool

* Fix init

* Tests

* Fix tests

* Tool save/from_hub/push_to_hub and tool->load_tool

* Clean push_to_hub and add app file

* Custom inference API for endpoints too

* Clean up

* old remote tool and new remote tool

* Make a requirements

* return_code adds tool creation

* Avoid redundancy between global variables

* Remote tools can be loaded

* Tests

* Text summarization tests

* Quality

* Properly mark tests

* Test the python interpreter

* And the CI shall be green.

* fix loading of additional tools

* Work on RemoteTool and fix tests

* General clean up

* Guard imports

* Fix tools

* docs: Fix broken link in 'How to add a model...'  (#23216)

fix link

* Get default endpoint from the Hub

* Add guide

* Simplify tool config

* Docs

* Some fixes

* Docs

* Docs

* Docs

* Fix code returned by agent

* Try this

* Match args with signature in remote tool

* Should fix python interpreter for Python 3.8

* Fix push_to_hub for tools

* Other fixes to push_to_hub

* Add API doc page

* Docs

* Docs

* Custom tools

* Pin tensorflow-probability (#23220)

* Pin tensorflow-probability

* [all-test]

* [all-test] Fix syntax for bash

* PoC for some chaining API

* Text to speech

* J'ai pris des libertés

* Rename

* Basic python interpreter

* Add agents

* Quality

* Add translation tool

* temp

* GenQA + LID + S2T

* Quality + word missing in translation

* Add open assistance, support f-strings in evaluate

* captioning + s2t fixes

* Style

* Refactor descriptions and remove chain

* Support errors and rename OpenAssistantAgent

* Add setup

* Deal with typos + example of inference API

* Some rename + README

* Fixes

* Update prompt

* Unwanted change

* Make sure everyone has a default

* One prompt to rule them all.

* SD

* Description

* Clean up remote tools

* More remote tools

* Add option to return code and update doc

* Image segmentation

* ControlNet

* Gradio demo

* Diffusers protection

* Lib protection

* ControlNet description

* Cleanup

* Style

* Remove accelerate and try to be reproducible

* No randomness

* Male Basic optional in token

* Clean description

* Better prompts

* Fix args eval in interpreter

* Add tool wrapper

* Tool on the Hub

* Style post-rebase

* Big refactor of descriptions, batch generation and evaluation for agents

* Make problems easier - interface to debug

* More problems, add python primitives

* Back to one prompt

* Remove dict for translation

* Be consistent

* Add prompts

* New version of the agent

* Evaluate new agents

* New endpoints agents

* Make all tools a dict variable

* Typo

* Add problems

* Add to big prompt

* Harmonize

* Add tools

* New evaluation

* Add more tools

* Build prompt with tools descriptions

* Tools on the Hub

* Let's chat!

* Cleanup

* Temporary bs4 safeguard

* Cache agents and clean up

* Blank init

* Fix evaluation for agents

* New format for tools on the Hub

* Add method to reset state

* Remove nestedness in tool config

* Really do it

* Use remote tools descriptions

* Work

* Clean up eval

* Changes

* Tools

* Tools

* tool

* Fix everything

* Use last result/assign for evaluation

* Prompt

* Remove hardcoded selection

* Evaluation for chat agents

* correct some spelling

* Small fixes

* Change summarization model (#23172)

* Fix link displayed

* Update description of the tool

* Fixes in chat prompt

* Custom tools, custom prompt

* Tool clean up

* save_pretrained and push_to_hub for tool

* Fix init

* Tests

* Fix tests

* Tool save/from_hub/push_to_hub and tool->load_tool

* Clean push_to_hub and add app file

* Custom inference API for endpoints too

* Clean up

* old remote tool and new remote tool

* Make a requirements

* return_code adds tool creation

* Avoid redundancy between global variables

* Remote tools can be loaded

* Tests

* Text summarization tests

* Quality

* Properly mark tests

* Test the python interpreter

* And the CI shall be green.

* Work on RemoteTool and fix tests

* fix loading of additional tools

* General clean up

* Guard imports

* Fix tools

* Get default endpoint from the Hub

* Simplify tool config

* Add guide

* Docs

* Some fixes

* Docs

* Docs

* Fix code returned by agent

* Try this

* Docs

* Match args with signature in remote tool

* Should fix python interpreter for Python 3.8

* Fix push_to_hub for tools

* Other fixes to push_to_hub

* Add API doc page

* Fixes

* Doc fixes

* Docs

* Fix audio

* Custom tools

* Audio fix

* Improve custom tools docstring

* Docstrings

* Trigger CI

* Mode docstrings

* More docstrings

* Improve custom tools

* Fix for remote tools

* Style

* Fix repo consistency

* Quality

* Tip

* Cleanup on doc

* Cleanup toc

* Add disclaimer for starcoder vs openai

* Remove disclaimer

* Small fixed in the prompts

* 4.29

* Update src/transformers/tools/agents.py

Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr>

* Complete documentation

* Small fixes

* Agent evaluation

* Note about gradio-tools & LC

* Clean up agents and prompt

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Note about gradio-tools & LC

* Add copyrights and address review comments

* Quality

* Add all language codes

* Add remote tool tests

* Move custom prompts to other docs

* Apply suggestions from code review

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* TTS tests

* Quality

---------

Co-authored-by: Lysandre <hi@lyand.re>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com>
Co-authored-by: Connor Henderson <connor.henderson@talkiatry.com>
Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
Co-authored-by: Lysandre <lysandre@huggingface.co>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2023-05-09 20:37:57 -04:00

125 lines
4.3 KiB
Python

# coding=utf-8
# Copyright 2023 HuggingFace Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
from transformers.testing_utils import CaptureStdout
from transformers.tools.python_interpreter import evaluate
# Fake function we will use as tool
def add_two(x):
return x + 2
class PythonInterpreterTester(unittest.TestCase):
def test_evaluate_assign(self):
code = "x = 3"
state = {}
result = evaluate(code, {}, state=state)
assert result == 3
self.assertDictEqual(state, {"x": 3})
code = "x = y"
state = {"y": 5}
result = evaluate(code, {}, state=state)
# evaluate returns the value of the last assignment.
assert result == 5
self.assertDictEqual(state, {"x": 5, "y": 5})
def test_evaluate_call(self):
code = "y = add_two(x)"
state = {"x": 3}
result = evaluate(code, {"add_two": add_two}, state=state)
assert result == 5
self.assertDictEqual(state, {"x": 3, "y": 5})
# Won't work without the tool
with CaptureStdout() as out:
result = evaluate(code, {}, state=state)
assert result is None
assert "tried to execute add_two" in out.out
def test_evaluate_constant(self):
code = "x = 3"
state = {}
result = evaluate(code, {}, state=state)
assert result == 3
self.assertDictEqual(state, {"x": 3})
def test_evaluate_dict(self):
code = "test_dict = {'x': x, 'y': add_two(x)}"
state = {"x": 3}
result = evaluate(code, {"add_two": add_two}, state=state)
self.assertDictEqual(result, {"x": 3, "y": 5})
self.assertDictEqual(state, {"x": 3, "test_dict": {"x": 3, "y": 5}})
def test_evaluate_expression(self):
code = "x = 3\ny = 5"
state = {}
result = evaluate(code, {}, state=state)
# evaluate returns the value of the last assignment.
assert result == 5
self.assertDictEqual(state, {"x": 3, "y": 5})
def test_evaluate_f_string(self):
code = "text = f'This is x: {x}.'"
state = {"x": 3}
result = evaluate(code, {}, state=state)
# evaluate returns the value of the last assignment.
assert result == "This is x: 3."
self.assertDictEqual(state, {"x": 3, "text": "This is x: 3."})
def test_evaluate_if(self):
code = "if x <= 3:\n y = 2\nelse:\n y = 5"
state = {"x": 3}
result = evaluate(code, {}, state=state)
# evaluate returns the value of the last assignment.
assert result == 2
self.assertDictEqual(state, {"x": 3, "y": 2})
state = {"x": 8}
result = evaluate(code, {}, state=state)
# evaluate returns the value of the last assignment.
assert result == 5
self.assertDictEqual(state, {"x": 8, "y": 5})
def test_evaluate_list(self):
code = "test_list = [x, add_two(x)]"
state = {"x": 3}
result = evaluate(code, {"add_two": add_two}, state=state)
self.assertListEqual(result, [3, 5])
self.assertDictEqual(state, {"x": 3, "test_list": [3, 5]})
def test_evaluate_name(self):
code = "y = x"
state = {"x": 3}
result = evaluate(code, {}, state=state)
assert result == 3
self.assertDictEqual(state, {"x": 3, "y": 3})
def test_evaluate_subscript(self):
code = "test_list = [x, add_two(x)]\ntest_list[1]"
state = {"x": 3}
result = evaluate(code, {"add_two": add_two}, state=state)
assert result == 5
self.assertDictEqual(state, {"x": 3, "test_list": [3, 5]})
code = "test_dict = {'x': x, 'y': add_two(x)}\ntest_dict['y']"
state = {"x": 3}
result = evaluate(code, {"add_two": add_two}, state=state)
assert result == 5
self.assertDictEqual(state, {"x": 3, "test_dict": {"x": 3, "y": 5}})