Skip to main content

An Extension of fabricatio aiming to extend the context llm could handle.

Project description

fabricatio-memory

An Extension of fabricatio aiming to extend the context llm could handle..


📦 Installation

This package is part of the fabricatio monorepo and can be installed as an optional dependency:

pip install fabricatio[memory]

Or install all components:

pip install fabricatio[full]

🔍 Overview

Provides essential tools for:

Context Expansion

This package enables the extension of the context that an LLM can handle. It does this by storing and retrieving relevant information from a memory system. For example, it can keep track of previous conversations, user preferences, and domain - specific knowledge, allowing the LLM to have a more comprehensive understanding of the current input.

Memory Management

It offers features for managing the memory used by the LLM. This includes tasks such as memory allocation, deallocation, and optimization. It ensures that the memory is used efficiently and that the LLM can access the necessary information quickly.

Integration with Fabricatio

The package is designed to work seamlessly with the Fabricatio framework. It can leverage the capabilities of Fabricatio's agent framework to manage the memory in a more intelligent way and integrate with other modules in the ecosystem.

...

🧩 Key Features

Long - Term Memory Storage

The long - term memory storage feature allows the LLM to store information over an extended period. It can save important data such as user profiles, historical conversations, and domain knowledge. This information can be retrieved later to provide more personalized and context - aware responses.

Short - Term Memory Buffer

The short - term memory buffer is used to store the most recent information. It helps the LLM to maintain a context for the current conversation and respond more coherently. For example, it can remember the last few messages in a chat session.

Memory Retrieval Mechanisms

The package provides efficient memory retrieval mechanisms. It can search through the stored memory based on keywords, context, or other criteria to find the relevant information. This ensures that the LLM can access the necessary data quickly and accurately.

...

🔗 Dependencies

Core dependencies:

  • fabricatio-core - Core interfaces and utilities This dependency provides the fundamental building blocks for the Fabricatio framework. It includes interfaces for task management, event handling, and data models. The fabricatio-memory package uses these interfaces to interact with other modules in the Fabricatio ecosystem and manage the memory effectively. ...

📄 License

MIT – see LICENSE

GitHub: github.com/Whth/fabricatio

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

fabricatio_memory-0.1.1.dev6-cp313-cp313-win_amd64.whl (2.3 MB view details)

Uploaded CPython 3.13Windows x86-64

fabricatio_memory-0.1.1.dev6-cp313-cp313-manylinux_2_34_x86_64.whl (2.9 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.34+ x86-64

fabricatio_memory-0.1.1.dev6-cp312-cp312-win_amd64.whl (2.3 MB view details)

Uploaded CPython 3.12Windows x86-64

fabricatio_memory-0.1.1.dev6-cp312-cp312-manylinux_2_34_x86_64.whl (2.9 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.34+ x86-64

File details

Details for the file fabricatio_memory-0.1.1.dev6-cp313-cp313-win_amd64.whl.

File metadata

File hashes

Hashes for fabricatio_memory-0.1.1.dev6-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 8d6d69e1f2914b33cf5c81073ed04ac67ef949d95cf76bd125153bb1a3e6e673
MD5 a76e1d5e77b7637b33a6ec280cfe03bb
BLAKE2b-256 c0903a0d8157922897bd15a15639d3ede2628c0bc3088f1548be6692fc36161a

See more details on using hashes here.

File details

Details for the file fabricatio_memory-0.1.1.dev6-cp313-cp313-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for fabricatio_memory-0.1.1.dev6-cp313-cp313-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 e4c8a802bdb3e44d371e6ef3be97571bf4a019e7eb001518ef5382f3baaf9d27
MD5 85a31e39ebf35fcbbc6c18cbed223b8f
BLAKE2b-256 c168b70f17f2e469ec156f53240b6f8ef48e2c413649eb98b674d7cd6dc65b26

See more details on using hashes here.

File details

Details for the file fabricatio_memory-0.1.1.dev6-cp312-cp312-win_amd64.whl.

File metadata

File hashes

Hashes for fabricatio_memory-0.1.1.dev6-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 d0c284fe1edf76abc580f3969a13b63b9420d953bba87675f7fdf611378ea6cb
MD5 5129046f43c08cf3e0615919427feadc
BLAKE2b-256 a4c4343fd5401278b845473c58a2d0308a65a31b8d7d9c311b1e29a9c58fb043

See more details on using hashes here.

File details

Details for the file fabricatio_memory-0.1.1.dev6-cp312-cp312-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for fabricatio_memory-0.1.1.dev6-cp312-cp312-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 945c22908cfb9600ad0673349a2731ce92abc2b9fdd272a23eb40495b7539599
MD5 abbbbacc495df3049be2440724b1cd9a
BLAKE2b-256 d1f6b9542391fc5f1c2aa028ad0c78310edea19f93862baa4fc3c02c1e63482e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page