tokens-lab
LLM utilities with agents, file parsing, and preprocessing built in.
Features
- Agent Framework: LangGraph-based agents with OpenAI integration
- File Text I/O: Parse PDFs, DOCX, PPTX, and images with ease
- Preprocessing: Text normalization and cleaning utilities
- Azure Integration: Azure Storage and service utilities
- ML Tools: String similarity and text analysis
- Utilities: Date, Excel, JSON, and Pandas helpers
- Logging: Structured logging support
- Exception Handling: Custom exception hierarchy
Installation
pip install tokens-lab
Quick Start
LLM Agent
from llm_lab.agent import Agent
from llm_lab.agent.litellm_client import LiteLLMClient
client = LiteLLMClient(model="gpt-4", api_key="your-api-key")
agent = Agent(client=client)
response = agent.process("Hello, how can you help me?")
File Parsing
from llm_lab.filetextio import parsers
content = parsers.parse_document("document.pdf")
Text Preprocessing
from llm_lab.preprocessing import text_normalization
clean_text = text_normalization.normalize_text("messy text ")
Documentation
For complete documentation, visit: https://pwc-me-adv-strategyand.github.io/LLM_Lab/
Requirements
- Python >= 3.10
License
MIT
Metadata
Release files for tokens-lab 0.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| tokens_lab-0.6.0.tar.gz | 22.6 kB | Without provenance | Details for tokens_lab-0.6.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| tokens_lab-0.6.0-py3-none-any.whl | Python 3 | none | any | Details for tokens_lab-0.6.0-py3-none-any.whl |
Total release size: 52.6 kB
Release files / tokens_lab-0.6.0.tar.gz
| Download URL | tokens_lab-0.6.0.tar.gz |
|---|---|
| Size | 22.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d20ef07aeb126f5920f5f08211fe767b848a8929f1eedbb52018cb78b88f1a00
|
|
BLAKE2b-256 checksum How to use checksums |
64c2ddb2479332af7f472d25a796d695634d8f91edac6c57cc5c267d2ca3a704
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.6
|
Release files / tokens_lab-0.6.0-py3-none-any.whl
| Download URL | tokens_lab-0.6.0-py3-none-any.whl |
|---|---|
| Size | 30.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ab3f4dd96f3da4ced6369b4fdcd646b9ac2b5c41f7a1933128ae7a0b37b9a4b9
|
|
BLAKE2b-256 checksum How to use checksums |
bb96508b06187d2f8a484edcb411760cc985ee1d3048f3b9dfb325b49b66eace
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.6
|
Security for tokens-lab 0.6.0
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.