Skip to main content

Long-term memory with TF-IDF retrieval — captured intelligence must be retrievable

Project description

archives

Long-term memory with TF-IDF retrieval. Captured intelligence must be retrievable, not just stored. The fleet's elephant memory.

Usage

from archives import Archives, Document

arch = Archives()
arch.store(Document(id="t1", content="Lyapunov stability in multi-agent systems", tags=["math"]))
arch.store(Document(id="t2", content="Bayesian belief updates for fleet trust", tags=["ml"]))

results = arch.query("stability convergence")
top = results.top(3)
for doc, score in top:
    print(f"{doc.id}: {score:.3f}")

Zero deps (no numpy). pip install archives

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 Distribution

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

cocapn_archives-0.1.0-py3-none-any.whl (3.4 kB view details)

Uploaded Python 3

File details

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

File metadata

File hashes

Hashes for cocapn_archives-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a50016e614fac1407f35e544abf1e213b5445d9a23bfc9354b76368f9b978e9b
MD5 57c436462d05ed6200fdc403f1396974
BLAKE2b-256 2210be4cd69a574c35497dcb444814890b911bc99c731e32000b56f5240ec155

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