Merge branch 'code_intepreter' into sd_and_debugcode_ut

This commit is contained in:
stellahsr 2024-01-12 16:58:05 +08:00
commit 192e2aa807
13 changed files with 180 additions and 855 deletions

633
.pylintrc
View file

@ -1,633 +0,0 @@
[MAIN]
# Analyse import fallback blocks. This can be used to support both Python 2 and
# 3 compatible code, which means that the block might have code that exists
# only in one or another interpreter, leading to false positives when analysed.
analyse-fallback-blocks=no
# Clear in-memory caches upon conclusion of linting. Useful if running pylint
# in a server-like mode.
clear-cache-post-run=no
# Load and enable all available extensions. Use --list-extensions to see a list
# all available extensions.
#enable-all-extensions=
# In error mode, messages with a category besides ERROR or FATAL are
# suppressed, and no reports are done by default. Error mode is compatible with
# disabling specific errors.
#errors-only=
# Always return a 0 (non-error) status code, even if lint errors are found.
# This is primarily useful in continuous integration scripts.
#exit-zero=
# A comma-separated list of package or module names from where C extensions may
# be loaded. Extensions are loading into the active Python interpreter and may
# run arbitrary code.
extension-pkg-allow-list=
# A comma-separated list of package or module names from where C extensions may
# be loaded. Extensions are loading into the active Python interpreter and may
# run arbitrary code. (This is an alternative name to extension-pkg-allow-list
# for backward compatibility.)
extension-pkg-whitelist=
# Return non-zero exit code if any of these messages/categories are detected,
# even if score is above --fail-under value. Syntax same as enable. Messages
# specified are enabled, while categories only check already-enabled messages.
fail-on=
# Specify a score threshold under which the program will exit with error.
fail-under=10
# Interpret the stdin as a python script, whose filename needs to be passed as
# the module_or_package argument.
#from-stdin=
# Files or directories to be skipped. They should be base names, not paths.
ignore=CVS, offline
# Add files or directories matching the regular expressions patterns to the
# ignore-list. The regex matches against paths and can be in Posix or Windows
# format. Because '\\' represents the directory delimiter on Windows systems,
# it can't be used as an escape character.
ignore-paths=
# Files or directories matching the regular expression patterns are skipped.
# The regex matches against base names, not paths. The default value ignores
# Emacs file locks
ignore-patterns=^\.#
# List of module names for which member attributes should not be checked
# (useful for modules/projects where namespaces are manipulated during runtime
# and thus existing member attributes cannot be deduced by static analysis). It
# supports qualified module names, as well as Unix pattern matching.
ignored-modules=
# Python code to execute, usually for sys.path manipulation such as
# pygtk.require().
#init-hook=
# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
# number of processors available to use, and will cap the count on Windows to
# avoid hangs.
jobs=1
# Control the amount of potential inferred values when inferring a single
# object. This can help the performance when dealing with large functions or
# complex, nested conditions.
limit-inference-results=100
# List of plugins (as comma separated values of python module names) to load,
# usually to register additional checkers.
load-plugins=
# Pickle collected data for later comparisons.
persistent=yes
# Minimum Python version to use for version dependent checks. Will default to
# the version used to run pylint.
py-version=3.9
# Discover python modules and packages in the file system subtree.
recursive=no
# Add paths to the list of the source roots. Supports globbing patterns. The
# source root is an absolute path or a path relative to the current working
# directory used to determine a package namespace for modules located under the
# source root.
source-roots=
# When enabled, pylint would attempt to guess common misconfiguration and emit
# user-friendly hints instead of false-positive error messages.
suggestion-mode=yes
# Allow loading of arbitrary C extensions. Extensions are imported into the
# active Python interpreter and may run arbitrary code.
unsafe-load-any-extension=no
# In verbose mode, extra non-checker-related info will be displayed.
#verbose=
[BASIC]
# Naming style matching correct argument names.
argument-naming-style=snake_case
# Regular expression matching correct argument names. Overrides argument-
# naming-style. If left empty, argument names will be checked with the set
# naming style.
#argument-rgx=
# Naming style matching correct attribute names.
attr-naming-style=snake_case
# Regular expression matching correct attribute names. Overrides attr-naming-
# style. If left empty, attribute names will be checked with the set naming
# style.
#attr-rgx=
# Bad variable names which should always be refused, separated by a comma.
bad-names=foo,
bar,
baz,
toto,
tutu,
tata
# Bad variable names regexes, separated by a comma. If names match any regex,
# they will always be refused
bad-names-rgxs=
# Naming style matching correct class attribute names.
class-attribute-naming-style=any
# Regular expression matching correct class attribute names. Overrides class-
# attribute-naming-style. If left empty, class attribute names will be checked
# with the set naming style.
#class-attribute-rgx=
# Naming style matching correct class constant names.
class-const-naming-style=UPPER_CASE
# Regular expression matching correct class constant names. Overrides class-
# const-naming-style. If left empty, class constant names will be checked with
# the set naming style.
#class-const-rgx=
# Naming style matching correct class names.
class-naming-style=PascalCase
# Regular expression matching correct class names. Overrides class-naming-
# style. If left empty, class names will be checked with the set naming style.
#class-rgx=
# Naming style matching correct constant names.
const-naming-style=UPPER_CASE
# Regular expression matching correct constant names. Overrides const-naming-
# style. If left empty, constant names will be checked with the set naming
# style.
#const-rgx=
# Minimum line length for functions/classes that require docstrings, shorter
# ones are exempt.
docstring-min-length=-1
# Naming style matching correct function names.
function-naming-style=snake_case
# Regular expression matching correct function names. Overrides function-
# naming-style. If left empty, function names will be checked with the set
# naming style.
#function-rgx=
# Good variable names which should always be accepted, separated by a comma.
good-names=i,
j,
k,
ex,
Run,
_
# Good variable names regexes, separated by a comma. If names match any regex,
# they will always be accepted
good-names-rgxs=
# Include a hint for the correct naming format with invalid-name.
include-naming-hint=no
# Naming style matching correct inline iteration names.
inlinevar-naming-style=any
# Regular expression matching correct inline iteration names. Overrides
# inlinevar-naming-style. If left empty, inline iteration names will be checked
# with the set naming style.
#inlinevar-rgx=
# Naming style matching correct method names.
method-naming-style=snake_case
# Regular expression matching correct method names. Overrides method-naming-
# style. If left empty, method names will be checked with the set naming style.
#method-rgx=
# Naming style matching correct module names.
module-naming-style=snake_case
# Regular expression matching correct module names. Overrides module-naming-
# style. If left empty, module names will be checked with the set naming style.
#module-rgx=
# Colon-delimited sets of names that determine each other's naming style when
# the name regexes allow several styles.
name-group=
# Regular expression which should only match function or class names that do
# not require a docstring.
no-docstring-rgx=^_
# List of decorators that produce properties, such as abc.abstractproperty. Add
# to this list to register other decorators that produce valid properties.
# These decorators are taken in consideration only for invalid-name.
property-classes=abc.abstractproperty
# Regular expression matching correct type alias names. If left empty, type
# alias names will be checked with the set naming style.
#typealias-rgx=
# Regular expression matching correct type variable names. If left empty, type
# variable names will be checked with the set naming style.
#typevar-rgx=
# Naming style matching correct variable names.
variable-naming-style=snake_case
# Regular expression matching correct variable names. Overrides variable-
# naming-style. If left empty, variable names will be checked with the set
# naming style.
#variable-rgx=
[CLASSES]
# Warn about protected attribute access inside special methods
check-protected-access-in-special-methods=no
# List of method names used to declare (i.e. assign) instance attributes.
defining-attr-methods=__init__,
__new__,
setUp,
asyncSetUp,
__post_init__
# List of member names, which should be excluded from the protected access
# warning.
exclude-protected=_asdict,_fields,_replace,_source,_make,os._exit
# List of valid names for the first argument in a class method.
valid-classmethod-first-arg=cls
# List of valid names for the first argument in a metaclass class method.
valid-metaclass-classmethod-first-arg=mcs
[DESIGN]
# List of regular expressions of class ancestor names to ignore when counting
# public methods (see R0903)
exclude-too-few-public-methods=
# List of qualified class names to ignore when counting class parents (see
# R0901)
ignored-parents=
# Maximum number of arguments for function / method.
max-args=5
# Maximum number of attributes for a class (see R0902).
max-attributes=7
# Maximum number of boolean expressions in an if statement (see R0916).
max-bool-expr=5
# Maximum number of branch for function / method body.
max-branches=12
# Maximum number of locals for function / method body.
max-locals=15
# Maximum number of parents for a class (see R0901).
max-parents=7
# Maximum number of public methods for a class (see R0904).
max-public-methods=20
# Maximum number of return / yield for function / method body.
max-returns=6
# Maximum number of statements in function / method body.
max-statements=50
# Minimum number of public methods for a class (see R0903).
min-public-methods=2
[EXCEPTIONS]
# Exceptions that will emit a warning when caught.
overgeneral-exceptions=builtins.BaseException,builtins.Exception
[FORMAT]
# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
expected-line-ending-format=
# Regexp for a line that is allowed to be longer than the limit.
ignore-long-lines=^\s*(# )?<?https?://\S+>?$
# Number of spaces of indent required inside a hanging or continued line.
indent-after-paren=4
# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1
# tab).
indent-string=' '
# Maximum number of characters on a single line.
max-line-length=120
# Maximum number of lines in a module.
max-module-lines=1000
# Allow the body of a class to be on the same line as the declaration if body
# contains single statement.
single-line-class-stmt=no
# Allow the body of an if to be on the same line as the test if there is no
# else.
single-line-if-stmt=no
[IMPORTS]
# List of modules that can be imported at any level, not just the top level
# one.
allow-any-import-level=
# Allow explicit reexports by alias from a package __init__.
allow-reexport-from-package=no
# Allow wildcard imports from modules that define __all__.
allow-wildcard-with-all=no
# Deprecated modules which should not be used, separated by a comma.
deprecated-modules=
# Output a graph (.gv or any supported image format) of external dependencies
# to the given file (report RP0402 must not be disabled).
ext-import-graph=
# Output a graph (.gv or any supported image format) of all (i.e. internal and
# external) dependencies to the given file (report RP0402 must not be
# disabled).
import-graph=
# Output a graph (.gv or any supported image format) of internal dependencies
# to the given file (report RP0402 must not be disabled).
int-import-graph=
# Force import order to recognize a module as part of the standard
# compatibility libraries.
known-standard-library=
# Force import order to recognize a module as part of a third party library.
known-third-party=enchant
# Couples of modules and preferred modules, separated by a comma.
preferred-modules=
[LOGGING]
# The type of string formatting that logging methods do. `old` means using %
# formatting, `new` is for `{}` formatting.
logging-format-style=old
# Logging modules to check that the string format arguments are in logging
# function parameter format.
logging-modules=logging
[MESSAGES CONTROL]
# Only show warnings with the listed confidence levels. Leave empty to show
# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE,
# UNDEFINED.
confidence=HIGH,
CONTROL_FLOW,
INFERENCE,
INFERENCE_FAILURE,
UNDEFINED
# Disable the message, report, category or checker with the given id(s). You
# can either give multiple identifiers separated by comma (,) or put this
# option multiple times (only on the command line, not in the configuration
# file where it should appear only once). You can also use "--disable=all" to
# disable everything first and then re-enable specific checks. For example, if
# you want to run only the similarities checker, you can use "--disable=all
# --enable=similarities". If you want to run only the classes checker, but have
# no Warning level messages displayed, use "--disable=all --enable=classes
# --disable=W".
disable=raw-checker-failed,
bad-inline-option,
locally-disabled,
file-ignored,
suppressed-message,
useless-suppression,
deprecated-pragma,
use-symbolic-message-instead,
import-error,
; C0114, C0115, C0116
# Enable the message, report, category or checker with the given id(s). You can
# either give multiple identifier separated by comma (,) or put this option
# multiple time (only on the command line, not in the configuration file where
# it should appear only once). See also the "--disable" option for examples.
enable=c-extension-no-member
[METHOD_ARGS]
# List of qualified names (i.e., library.method) which require a timeout
# parameter e.g. 'requests.api.get,requests.api.post'
timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request
[MISCELLANEOUS]
# List of note tags to take in consideration, separated by a comma.
notes=FIXME,
XXX,
TODO
# Regular expression of note tags to take in consideration.
notes-rgx=
[REFACTORING]
# Maximum number of nested blocks for function / method body
max-nested-blocks=5
# Complete name of functions that never returns. When checking for
# inconsistent-return-statements if a never returning function is called then
# it will be considered as an explicit return statement and no message will be
# printed.
never-returning-functions=sys.exit,argparse.parse_error
[REPORTS]
# Python expression which should return a score less than or equal to 10. You
# have access to the variables 'fatal', 'error', 'warning', 'refactor',
# 'convention', and 'info' which contain the number of messages in each
# category, as well as 'statement' which is the total number of statements
# analyzed. This score is used by the global evaluation report (RP0004).
evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10))
# Template used to display messages. This is a python new-style format string
# used to format the message information. See doc for all details.
msg-template=
# Set the output format. Available formats are text, parseable, colorized, json
# and msvs (visual studio). You can also give a reporter class, e.g.
# mypackage.mymodule.MyReporterClass.
#output-format=
# Tells whether to display a full report or only the messages.
reports=no
# Activate the evaluation score.
score=yes
[SIMILARITIES]
# Comments are removed from the similarity computation
ignore-comments=yes
# Docstrings are removed from the similarity computation
ignore-docstrings=yes
# Imports are removed from the similarity computation
ignore-imports=yes
# Signatures are removed from the similarity computation
ignore-signatures=yes
# Minimum lines number of a similarity.
min-similarity-lines=4
[SPELLING]
# Limits count of emitted suggestions for spelling mistakes.
max-spelling-suggestions=4
# Spelling dictionary name. No available dictionaries : You need to install
# both the python package and the system dependency for enchant to work..
spelling-dict=
# List of comma separated words that should be considered directives if they
# appear at the beginning of a comment and should not be checked.
spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:
# List of comma separated words that should not be checked.
spelling-ignore-words=
# A path to a file that contains the private dictionary; one word per line.
spelling-private-dict-file=
# Tells whether to store unknown words to the private dictionary (see the
# --spelling-private-dict-file option) instead of raising a message.
spelling-store-unknown-words=no
[STRING]
# This flag controls whether inconsistent-quotes generates a warning when the
# character used as a quote delimiter is used inconsistently within a module.
check-quote-consistency=no
# This flag controls whether the implicit-str-concat should generate a warning
# on implicit string concatenation in sequences defined over several lines.
check-str-concat-over-line-jumps=no
[TYPECHECK]
# List of decorators that produce context managers, such as
# contextlib.contextmanager. Add to this list to register other decorators that
# produce valid context managers.
contextmanager-decorators=contextlib.contextmanager
# List of members which are set dynamically and missed by pylint inference
# system, and so shouldn't trigger E1101 when accessed. Python regular
# expressions are accepted.
generated-members=
# Tells whether to warn about missing members when the owner of the attribute
# is inferred to be None.
ignore-none=yes
# This flag controls whether pylint should warn about no-member and similar
# checks whenever an opaque object is returned when inferring. The inference
# can return multiple potential results while evaluating a Python object, but
# some branches might not be evaluated, which results in partial inference. In
# that case, it might be useful to still emit no-member and other checks for
# the rest of the inferred objects.
ignore-on-opaque-inference=yes
# List of symbolic message names to ignore for Mixin members.
ignored-checks-for-mixins=no-member,
not-async-context-manager,
not-context-manager,
attribute-defined-outside-init
# List of class names for which member attributes should not be checked (useful
# for classes with dynamically set attributes). This supports the use of
# qualified names.
ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace
# Show a hint with possible names when a member name was not found. The aspect
# of finding the hint is based on edit distance.
missing-member-hint=yes
# The minimum edit distance a name should have in order to be considered a
# similar match for a missing member name.
missing-member-hint-distance=1
# The total number of similar names that should be taken in consideration when
# showing a hint for a missing member.
missing-member-max-choices=1
# Regex pattern to define which classes are considered mixins.
mixin-class-rgx=.*[Mm]ixin
# List of decorators that change the signature of a decorated function.
signature-mutators=
[VARIABLES]
# List of additional names supposed to be defined in builtins. Remember that
# you should avoid defining new builtins when possible.
additional-builtins=
# Tells whether unused global variables should be treated as a violation.
allow-global-unused-variables=yes
# List of names allowed to shadow builtins
allowed-redefined-builtins=
# List of strings which can identify a callback function by name. A callback
# name must start or end with one of those strings.
callbacks=cb_,
_cb
# A regular expression matching the name of dummy variables (i.e. expected to
# not be used).
dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
# Argument names that match this expression will be ignored.
ignored-argument-names=_.*|^ignored_|^unused_
# Tells whether we should check for unused import in __init__ files.
init-import=no
# List of qualified module names which can have objects that can redefine
# builtins.
redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io

View file

@ -13,7 +13,9 @@ async def main(requirement: str = ""):
if __name__ == "__main__":
sd_url = 'http://106.75.10.65:19094'
requirement = f"I want to generate an image of a beautiful girl using the stable diffusion text2image tool, sd_url={sd_url}"
sd_url = "http://106.75.10.65:19094"
requirement = (
f"I want to generate an image of a beautiful girl using the stable diffusion text2image tool, sd_url={sd_url}"
)
asyncio.run(main(requirement))

View file

@ -20,14 +20,16 @@ from metagpt.prompts.ml_engineer import (
GENERATE_CODE_PROMPT,
ML_TOOL_USAGE_PROMPT,
SELECT_FUNCTION_TOOLS,
TASK_MODULE_MAP,
TASK_SPECIFIC_PROMPT,
TOOL_RECOMMENDATION_PROMPT,
TOOL_USAGE_PROMPT,
)
from metagpt.schema import Message, Plan
from metagpt.tools import TOOL_TYPE_MAPPINGS
from metagpt.utils.common import create_func_config, remove_comments
TOOL_TYPE_MODULE = {k: v.module for k, v in TOOL_TYPE_MAPPINGS.items()}
TOOL_TYPE_USAGE_PROMPT = {k: v.usage_prompt for k, v in TOOL_TYPE_MAPPINGS.items()}
class BaseWriteAnalysisCode(Action):
DEFAULT_SYSTEM_MSG: str = """You are Code Interpreter, a world-class programmer that can complete any goal by executing code. Strictly follow the plan and generate code step by step. Each step of the code will be executed on the user's machine, and the user will provide the code execution results to you.**Notice: The code for the next step depends on the code for the previous step. Must reuse variables in the lastest other code directly, dont creat it again, it is very import for you. Use !pip install in a standalone block to install missing packages.Usually the libraries you need are already installed.Dont check if packages already imported.**""" # prompt reference: https://github.com/KillianLucas/open-interpreter/blob/v0.1.4/interpreter/system_message.txt
@ -171,9 +173,11 @@ class WriteCodeWithTools(BaseWriteAnalysisCode):
plan: Plan = None,
**kwargs,
) -> str:
task_type = plan.current_task.task_type
available_tools = self.available_tools.get(task_type, {})
special_prompt = TASK_SPECIFIC_PROMPT.get(task_type, "")
tool_type = (
plan.current_task.task_type
) # find tool type from task type through exact match, can extend to retrieval in the future
available_tools = self.available_tools.get(tool_type, {})
special_prompt = TOOL_TYPE_USAGE_PROMPT.get(tool_type, "")
code_steps = plan.current_task.code_steps
finished_tasks = plan.get_finished_tasks()
@ -189,10 +193,10 @@ class WriteCodeWithTools(BaseWriteAnalysisCode):
recommend_tools = await self._tool_recommendation(
plan.current_task.instruction, code_steps, available_tools
)
tool_catalog = self._parse_recommend_tools(task_type, recommend_tools)
tool_catalog = self._parse_recommend_tools(tool_type, recommend_tools)
logger.info(f"Recommended tools: \n{recommend_tools}")
module_name = TASK_MODULE_MAP[task_type]
module_name = TOOL_TYPE_MODULE[tool_type]
tools_instruction = TOOL_USAGE_PROMPT.format(
special_prompt=special_prompt, module_name=module_name, tool_catalog=tool_catalog
@ -215,9 +219,9 @@ class WriteCodeWithToolsML(WriteCodeWithTools):
column_info: str = "",
**kwargs,
) -> Tuple[List[Message], str]:
task_type = plan.current_task.task_type
available_tools = self.available_tools.get(task_type, {})
special_prompt = TASK_SPECIFIC_PROMPT.get(task_type, "")
tool_type = plan.current_task.task_type
available_tools = self.available_tools.get(tool_type, {})
special_prompt = TOOL_TYPE_USAGE_PROMPT.get(tool_type, "")
code_steps = plan.current_task.code_steps
finished_tasks = plan.get_finished_tasks()
@ -230,10 +234,10 @@ class WriteCodeWithToolsML(WriteCodeWithTools):
recommend_tools = await self._tool_recommendation(
plan.current_task.instruction, code_steps, available_tools
)
tool_catalog = self._parse_recommend_tools(task_type, recommend_tools)
tool_catalog = self._parse_recommend_tools(tool_type, recommend_tools)
logger.info(f"Recommended tools: \n{recommend_tools}")
module_name = TASK_MODULE_MAP[task_type]
module_name = TOOL_TYPE_MODULE[tool_type]
prompt = ML_TOOL_USAGE_PROMPT.format(
user_requirement=plan.goal,

View file

@ -12,6 +12,7 @@ from metagpt.actions import Action
from metagpt.logs import logger
from metagpt.prompts.ml_engineer import ASSIGN_TASK_TYPE_CONFIG, ASSIGN_TASK_TYPE_PROMPT
from metagpt.schema import Message, Plan, Task
from metagpt.tools import TOOL_TYPE_MAPPINGS
from metagpt.utils.common import CodeParser, create_func_config
@ -46,7 +47,10 @@ class WritePlan(Action):
List[Dict]: tasks with task type assigned
"""
task_list = "\n".join([f"Task {task['task_id']}: {task['instruction']}" for task in tasks])
prompt = ASSIGN_TASK_TYPE_PROMPT.format(task_list=task_list)
task_type_desc = "\n".join([f"- **{item.name}**: {item.desc}" for item in TOOL_TYPE_MAPPINGS.values()])
prompt = ASSIGN_TASK_TYPE_PROMPT.format(
task_list=task_list, task_type_desc=task_type_desc
) # task types are set to be the same as tool types, for now
tool_config = create_func_config(ASSIGN_TASK_TYPE_CONFIG)
rsp = await self.llm.aask_code(prompt, **tool_config)
task_type_list = rsp["task_type"]

View file

@ -71,6 +71,7 @@ SOURCE_ROOT = METAGPT_ROOT / "metagpt"
PROMPT_PATH = SOURCE_ROOT / "prompts"
SKILL_DIRECTORY = SOURCE_ROOT / "skills"
TOOL_SCHEMA_PATH = METAGPT_ROOT / "metagpt/tools/functions/schemas"
TOOL_LIBS_PATH = METAGPT_ROOT / "metagpt/tools/functions/libs"
# REAL CONSTS

View file

@ -54,12 +54,7 @@ Please assign a task type to each task in the list below from the given categori
{task_list}
## All Task Type:
- **feature_engineering**: Only for creating new columns for input data.
- **data_preprocess**: Only for changing value inplace.
- **model_train**: Only for training model.
- **model_evaluate**: Only for evaluating model.
- **stable_diffusion**: Related to text2image, image2image using stable diffusion model.
- **other**: Any tasks that do not fit into the previous categories, such as visualization, summarizing findings, etc.
{task_type_desc}
"""
ASSIGN_TASK_TYPE_CONFIG = {
@ -279,53 +274,3 @@ for col in num_cols:
- The output code should contain all steps implemented correctly in 'Code Steps'.
"""
# - If 'Code Steps' contains step done in 'Done Tasks', such as reading data, don't repeat it.
DATA_PREPROCESS_PROMPT = """
The current task is about data preprocessing, please note the following:
- Monitor data types per column, applying appropriate methods.
- Ensure operations are on existing dataset columns.
- Avoid writing processed data to files.
- Avoid any change to label column, such as standardization, etc.
- Prefer alternatives to one-hot encoding for categorical data.
- Only encode or scale necessary columns to allow for potential feature-specific engineering tasks (like time_extract, binning, extraction, etc.) later.
- Each step do data preprocessing to train, must do same for test separately at the same time.
"""
FEATURE_ENGINEERING_PROMPT = """
The current task is about feature engineering. when performing it, please adhere to the following principles:
- Generate as diverse features as possible to improve the model's performance step-by-step.
- If potential impactful features are not included in 'Code Steps', add new steps to generate them.
- Avoid creating redundant or excessively numerous features in one step.
- Exclude ID columns from feature generation and remove them.
- Each step do feature engineering to train, must do same for test separately at the same time.
- Avoid using the label column to create features, except for cat encoding.
- Use the data from previous task result if exist, do not mock or reload data yourself.
"""
MODEL_TRAIN_PROMPT = """
The current task is about training a model, please ensure high performance:
- Keep in mind that your user prioritizes results and is highly focused on model performance. So, when needed, feel free to use models of any complexity to improve effectiveness, such as lightGBM, XGBoost, CatBoost, etc.
- If non-numeric columns exist, perform label encode together with all steps.
- Use the data from previous task result directly, do not mock or reload data yourself.
- Set suitable hyperparameters for the model, make metrics as high as possible.
"""
MODEL_EVALUATE_PROMPT = """
The current task is about evaluating a model, please note the following:
- Ensure that the evaluated data is same processed as the training data. If not, remember use object in 'Done Tasks' to transform the data.
- Use trained model from previous task result directly, do not mock or reload model yourself.
"""
TASK_SPECIFIC_PROMPT = {
"data_preprocess": DATA_PREPROCESS_PROMPT,
"feature_engineering": FEATURE_ENGINEERING_PROMPT,
"model_train": MODEL_TRAIN_PROMPT,
"model_evaluate": MODEL_EVALUATE_PROMPT,
}
TASK_MODULE_MAP = {
"data_preprocess": "metagpt.tools.functions.libs.data_preprocess",
"feature_engineering": "metagpt.tools.functions.libs.feature_engineering",
"udf": "metagpt.tools.functions.libs.udf",
"stable_diffusion": "metagpt.tools.sd_engine",
}

View file

@ -0,0 +1,39 @@
# Prompt for using tools of "data_preprocess" type
DATA_PREPROCESS_PROMPT = """
The current task is about data preprocessing, please note the following:
- Monitor data types per column, applying appropriate methods.
- Ensure operations are on existing dataset columns.
- Avoid writing processed data to files.
- Avoid any change to label column, such as standardization, etc.
- Prefer alternatives to one-hot encoding for categorical data.
- Only encode or scale necessary columns to allow for potential feature-specific engineering tasks (like time_extract, binning, extraction, etc.) later.
- Each step do data preprocessing to train, must do same for test separately at the same time.
"""
# Prompt for using tools of "feature_engineering" type
FEATURE_ENGINEERING_PROMPT = """
The current task is about feature engineering. when performing it, please adhere to the following principles:
- Generate as diverse features as possible to improve the model's performance step-by-step.
- If potential impactful features are not included in 'Code Steps', add new steps to generate them.
- Avoid creating redundant or excessively numerous features in one step.
- Exclude ID columns from feature generation and remove them.
- Each step do feature engineering to train, must do same for test separately at the same time.
- Avoid using the label column to create features, except for cat encoding.
- Use the data from previous task result if exist, do not mock or reload data yourself.
"""
# Prompt for using tools of "model_train" type
MODEL_TRAIN_PROMPT = """
The current task is about training a model, please ensure high performance:
- Keep in mind that your user prioritizes results and is highly focused on model performance. So, when needed, feel free to use models of any complexity to improve effectiveness, such as lightGBM, XGBoost, CatBoost, etc.
- If non-numeric columns exist, perform label encode together with all steps.
- Use the data from previous task result directly, do not mock or reload data yourself.
- Set suitable hyperparameters for the model, make metrics as high as possible.
"""
# Prompt for using tools of "model_evaluate" type
MODEL_EVALUATE_PROMPT = """
The current task is about evaluating a model, please note the following:
- Ensure that the evaluated data is same processed as the training data. If not, remember use object in 'Done Tasks' to transform the data.
- Use trained model from previous task result directly, do not mock or reload model yourself.
"""

View file

@ -6,9 +6,18 @@
@File : __init__.py
"""
from enum import Enum
from pydantic import BaseModel
from metagpt.const import TOOL_LIBS_PATH
from metagpt.prompts.tool_type import (
DATA_PREPROCESS_PROMPT,
FEATURE_ENGINEERING_PROMPT,
MODEL_TRAIN_PROMPT,
MODEL_EVALUATE_PROMPT,
)
class SearchEngineType(Enum):
SERPAPI_GOOGLE = "serpapi"
@ -27,3 +36,50 @@ class WebBrowserEngineType(Enum):
def __missing__(cls, key):
"""Default type conversion"""
return cls.CUSTOM
class ToolType(BaseModel):
name: str
module: str = ""
desc: str
usage_prompt: str = ""
TOOL_TYPE_MAPPINGS = {
"data_preprocess": ToolType(
name="data_preprocess",
module=str(TOOL_LIBS_PATH / "data_preprocess"),
desc="Only for changing value inplace.",
usage_prompt=DATA_PREPROCESS_PROMPT,
),
"feature_engineering": ToolType(
name="feature_engineering",
module=str(TOOL_LIBS_PATH / "feature_engineering"),
desc="Only for creating new columns for input data.",
usage_prompt=FEATURE_ENGINEERING_PROMPT,
),
"model_train": ToolType(
name="model_train",
module="",
desc="Only for training model.",
usage_prompt=MODEL_TRAIN_PROMPT,
),
"model_evaluate": ToolType(
name="model_evaluate",
module="",
desc="Only for evaluating model.",
usage_prompt=MODEL_EVALUATE_PROMPT,
),
"stable_diffusion": ToolType(
name="stable_diffusion",
module="metagpt.tools.sd_engine",
desc="Related to text2image, image2image using stable diffusion model.",
usage_prompt="",
),
"other": ToolType(
name="other",
module="",
desc="Any tasks that do not fit into the previous categories",
usage_prompt="",
),
}

View file

@ -60,6 +60,7 @@ def llm_mock(rsp_cache, mocker, request):
llm.rsp_cache = rsp_cache
mocker.patch("metagpt.provider.base_llm.BaseLLM.aask", llm.aask)
mocker.patch("metagpt.provider.base_llm.BaseLLM.aask_batch", llm.aask_batch)
mocker.patch("metagpt.provider.openai_api.OpenAILLM.aask_code", llm.aask_code)
yield mocker
if hasattr(request.node, "test_outcome") and request.node.test_outcome.passed:
if llm.rsp_candidates:
@ -67,7 +68,7 @@ def llm_mock(rsp_cache, mocker, request):
cand_key = list(rsp_candidate.keys())[0]
cand_value = list(rsp_candidate.values())[0]
if cand_key not in llm.rsp_cache:
logger.info(f"Added '{cand_key[:100]} ... -> {cand_value[:20]} ...' to response cache")
logger.info(f"Added '{cand_key[:100]} ... -> {str(cand_value)[:20]} ...' to response cache")
llm.rsp_cache.update(rsp_candidate)
RSP_CACHE_NEW.update(rsp_candidate)

File diff suppressed because one or more lines are too long

View file

@ -1,4 +1,12 @@
from metagpt.actions.write_plan import Plan, Task, precheck_update_plan_from_rsp
import pytest
from metagpt.actions.write_plan import (
Plan,
Task,
WritePlan,
precheck_update_plan_from_rsp,
)
from metagpt.schema import Message
def test_precheck_update_plan_from_rsp():
@ -12,3 +20,12 @@ def test_precheck_update_plan_from_rsp():
invalid_rsp = "wrong"
success, _ = precheck_update_plan_from_rsp(invalid_rsp, plan)
assert not success
@pytest.mark.asyncio
async def test_write_plan():
rsp = await WritePlan().run(context=[Message("run analysis on sklearn iris dataset", role="user")])
assert "task_id" in rsp
assert "instruction" in rsp
assert "json" not in rsp # the output should be the content inside ```json ```

View file

@ -0,0 +1,13 @@
import pytest
from metagpt.logs import logger
from metagpt.roles.code_interpreter import CodeInterpreter
@pytest.mark.asyncio
async def test_code_interpreter():
requirement = "Run data analysis on sklearn Iris dataset, include a plot"
ci = CodeInterpreter(goal=requirement, auto_run=True, use_tools=False)
rsp = await ci.run(requirement)
logger.info(rsp)
assert len(rsp.content) > 0

View file

@ -1,10 +1,16 @@
from typing import Optional
import json
from typing import Optional, Union
from metagpt.config import CONFIG
from metagpt.logs import log_llm_stream, logger
from metagpt.provider.azure_openai_api import AzureOpenAILLM
from metagpt.provider.openai_api import OpenAILLM
from metagpt.schema import Message
OriginalLLM = OpenAILLM if not CONFIG.openai_api_type else AzureOpenAILLM
class MockLLM(OpenAILLM):
class MockLLM(OriginalLLM):
def __init__(self, allow_open_api_call):
super().__init__()
self.allow_open_api_call = allow_open_api_call
@ -58,6 +64,15 @@ class MockLLM(OpenAILLM):
context.append(self._assistant_msg(rsp_text))
return self._extract_assistant_rsp(context)
async def original_aask_code(self, messages: Union[str, Message, list[dict]], **kwargs) -> dict:
"""
A copy of metagpt.provider.openai_api.OpenAILLM.aask_code, we can't use super().aask because it will be mocked.
Since openai_api.OpenAILLM.aask_code is different from base_llm.BaseLLM.aask_code, we use the former.
"""
messages = self._process_message(messages)
rsp = await self._achat_completion_function(messages, **kwargs)
return self.get_choice_function_arguments(rsp)
async def aask(
self,
msg: str,
@ -78,6 +93,12 @@ class MockLLM(OpenAILLM):
rsp = await self._mock_rsp(msg_key, self.original_aask_batch, msgs, timeout)
return rsp
async def aask_code(self, messages: Union[str, Message, list[dict]], **kwargs) -> dict:
messages = self._process_message(messages)
msg_key = json.dumps(messages, ensure_ascii=False)
rsp = await self._mock_rsp(msg_key, self.original_aask_code, messages, **kwargs)
return rsp
async def _mock_rsp(self, msg_key, ask_func, *args, **kwargs):
if msg_key not in self.rsp_cache:
if not self.allow_open_api_call: