Usage#
ML Research Tools provides a command-line interface for accessing various tools. This guide covers basic usage patterns and common examples.
Command-Line Interface#
The package provides a single command-line entry point ml_research_tools with subcommands for each tool:
ml_research_tools [global options] <tool-name> [tool options]
Usage: ml_research_tools [-h] [--config CONFIG]
[--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}]
[--log-file LOG_FILE] [-v] [--redis-host REDIS_HOST]
[--redis-port REDIS_PORT] [--redis-db REDIS_DB]
[--redis-password REDIS_PASSWORD] [--redis-disable]
[--redis-recache] [--llm-preset LLM_PRESET]
[--llm-tier LLM_TIER] [--llm-api-key LLM_API_KEY]
[--llm-base-url LLM_BASE_URL] [--llm-model LLM_MODEL]
[--llm-max-tokens LLM_MAX_TOKENS]
[--llm-temperature LLM_TEMPERATURE]
[--llm-top-p LLM_TOP_P]
[--llm-retry-attempts LLM_RETRY_ATTEMPTS]
[--llm-retry-delay LLM_RETRY_DELAY] [--list-presets]
[--list-tools]
[--rich-capture-output RICH_CAPTURE_OUTPUT]
{help,ask-document,wandb-downloader,kube-pod-forward,latex-grammar}
...
ML Research Tools - A collection of utilities for ML research
Options:
-h, --help show this help message and exit
--list-presets List available LLM presets and exit
--list-tools List available tools and exit
--rich-capture-output RICH_CAPTURE_OUTPUT
Capture output in a rich format to this file
Configuration:
--config CONFIG Path to configuration file (default:
~/.config/ml_research_tools/config.yaml)
Logging:
--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}
Logging level
--log-file LOG_FILE Path to log file
-v, --verbose Enable verbose logging
Redis:
--redis-host REDIS_HOST
Redis host
--redis-port REDIS_PORT
Redis port
--redis-db REDIS_DB Redis database number
--redis-password REDIS_PASSWORD
Redis password
--redis-disable Disable Redis caching
--redis-recache Disable Redis caching retrieval, but allow saving
Llm:
--llm-preset LLM_PRESET
LLM preset name to use (e.g., 'standard', 'premium')
--llm-tier LLM_TIER LLM tier to use (e.g., 'standard', 'premium')
--llm-api-key LLM_API_KEY
API key for LLM service
--llm-base-url LLM_BASE_URL
Base URL for the LLM API endpoint
--llm-model LLM_MODEL
LLM model to use
--llm-max-tokens LLM_MAX_TOKENS
Maximum tokens for LLM response
--llm-temperature LLM_TEMPERATURE
Temperature for LLM sampling
--llm-top-p LLM_TOP_P
Top-p value for LLM sampling
--llm-retry-attempts LLM_RETRY_ATTEMPTS
Number of retry attempts for LLM API calls
--llm-retry-delay LLM_RETRY_DELAY
Delay between retry attempts for LLM API calls
(seconds)
Tools:
{help,ask-document,wandb-downloader,kube-pod-forward,latex-grammar}
Available tools
help Display help information about available tools
ask-document Interactive chat with document content using LLMs
wandb-downloader Download artifacts and runs from Weights & Biases
kube-pod-forward Forward port to a Kubernetes pod with a specific name
pattern.
latex-grammar Check and improve LaTeX grammar and style with LLM
Available Tools#
The toolkit includes the following tools:
LaTeX Grammar Tool#
Check and improve grammar in LaTeX documents:
ml_research_tools latex-grammar paper.tex --output-file improved_paper.tex
Ask Document Tool#
Chat with document content using LLMs:
ml_research_tools ask-document research_paper.pdf
W&B Downloader Tool#
Download Weights & Biases run logs:
ml_research_tools wandb-downloader --entity myuser --project myproject
Kubernetes Pod Forward Tool#
Forward ports to Kubernetes pods:
ml_research_tools kube-pod-forward --namespace default web-app
Scripting#
ML Research Tools can be used programmatically in Python scripts:
from ml_research_tools.tex import LatexGrammarTool
from ml_research_tools.core.config import Config
from ml_research_tools.core.service_provider import ServiceProvider
from ml_research_tools.core.service_factories import register_common_services
# Create configuration
config = Config.from_dict({
"llm": {
"default": "standard",
"presets": {
"standard": {
"api_key": "your-api-key",
"model": "gpt-3.5-turbo",
"tier": "standard"
}
}
}
})
# Create service provider
services = ServiceProvider(config)
register_common_services(services)
# Initialize the tool
tool = LatexGrammarTool(services)
# Create args object with required parameters
class Args:
pass
args = Args()
args.input_file = "paper.tex"
args.output_file = "improved_paper.tex"
# Execute the tool
tool.execute(config, args)
Getting Help#
To see a list of available tools:
ml_research_tools --list-tools
To get help for a specific tool:
ml_research_tools TOOL --help
# For example:
ml_research_tools latex-grammar --help
LLM Features#
The tools that use LLM capabilities support selecting different models:
# Use a specific preset
ml_research_tools --llm-preset=premium latex-grammar paper.tex
# Use a specific tier
ml_research_tools --llm-tier=standard latex-grammar paper.tex
To list available LLM presets:
ml_research_tools --list-presets
Using Redis Caching#
Many tools support Redis caching to speed up repeated operations:
# Enable Redis caching
ml_research_tools --redis-host=localhost --redis-port=6379 latex-grammar paper.tex
# Disable Redis caching
ml_research_tools --redis-disable latex-grammar paper.tex
Python API#
You can also use ML Research Tools directly in your Python code:
from ml_research_tools.core.config import Config
from ml_research_tools.core.service_provider import ServiceProvider
from ml_research_tools.core.service_factories import register_common_services
from ml_research_tools.tex import LatexGrammarTool
# Load configuration
config = Config.from_dict({
"llm": {
"default": "standard",
"presets": {
"standard": {
"model": "gpt-3.5-turbo",
"api_key": "your-api-key",
"tier": "standard"
}
}
}
})
# Set up services
services = ServiceProvider(config)
register_common_services(services)
# Create tool instance
tool = LatexGrammarTool(services)
# Execute the tool
exit_code = tool.execute(config, args)
For more detailed examples, see the individual tool documentation pages.