Skip to main content

AI Memory that Actually Works — Graph-based memory for LLM applications

Project description

Vektori Python SDK

AI Memory that Actually Works — Graph-based memory for LLM applications.

Installation

pip install vektori

Quick Start

from vektori import Vektori

# Cloud
memory = Vektori(api_key="vk_your_key")

# Self-hosted
memory = Vektori(url="http://localhost:8080")

# Store memories
memory.ingest(
    user_id="user_123",
    messages=[
        {"role": "user", "content": "I love pizza"},
        {"role": "assistant", "content": "Noted!"}
    ]
)

# Retrieve context
result = memory.retrieve(user_id="user_123", query="favorite food")
print(result.context)  # "User loves pizza"

Documentation

Full documentation: https://docs.vektori.cloud

License

MIT

Project details


Download files

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

Source Distribution

vektori-0.1.0.tar.gz (5.1 kB view details)

Uploaded Source

Built Distribution

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

vektori-0.1.0-py3-none-any.whl (5.2 kB view details)

Uploaded Python 3

File details

Details for the file vektori-0.1.0.tar.gz.

File metadata

  • Download URL: vektori-0.1.0.tar.gz
  • Upload date:
  • Size: 5.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for vektori-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9e8b49969896fe6684cdbb0e65796831262c1c5e84444a0a80ce71f364ea336c
MD5 0edf7a5f0756a76a620c937fb577c770
BLAKE2b-256 c6d185e7c5942ee81ecd1e9c8945b37dd903aa98955027c1cf6636b1c5b09369

See more details on using hashes here.

File details

Details for the file vektori-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: vektori-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for vektori-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3a600f01ff8863f4865e2496efad857cce5a097595b091e9f01a4c0c555bd7e6
MD5 2606b4fb4a078d7b3770e395c9118760
BLAKE2b-256 84051dafb85ed78c717945a8327bf5719a430363a0a403283f028e9b0c62b508

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