Skip to main content

A Python SDK for Chatsee AI.

Project description

Chatsee SDK (Python)

Installation

pip install chatsee-ai

Environment deployment (QA / Demo / GCP)

The SDK supports one package and you select the environment by setting api_base_url to an alias: "qa" | "demo" | "gcp" | "gcp-demo".

Classifiers source (redaction)

By default, the SDK always fetches redaction classifiers from QA (qa) regardless of the selected environment.

QA

Demo

  • Alias: demohttps://demo-api.chatsee.ai:8000
  • Interaction endpoint: /v1/api/process_interaction
  • Classifiers endpoint: /v1/redaction/fetch-classifiers
  • API docs: demo process_interaction

GCP QA

  • Alias: gcphttps://gcp-qa.chatsee.ai/api
  • Interaction endpoint: /v1/api/process_interaction
  • Classifiers endpoint: /v1/redaction/fetch-classifiers

GCP Demo

  • Alias: gcp-demohttps://gcp-demo.chatsee.ai/api
  • Interaction endpoint: /v1/api/process_interaction
  • Classifiers endpoint: /v1/redaction/fetch-classifiers

Usage (tracking)

from chatsee import ChatseeTracker

tracker = ChatseeTracker(
    agent_id="agent_1",
    tenant_id="tenant_1",
    api_base_url="qa",  # or "demo" / "gcp" / "gcp-demo"
    redaction_enabled=True,  # optional: locally redact before sending
)

tracker.start_turn("My email is test@example.com", metadata={"any": "metadata"})
tracker.end_turn("Thanks!")

Usage (redaction as an SDK feature)

Module-level chatsee.redact()

from chatsee import redact

redacted = redact(
    {"message": "Card 4111 1111 1111 1111", "email": "a@b.com"},
    api_base_url="qa",
    fields_to_redact="*",
    verify_ssl=True,
)

Tracker instance tracker.redact()

redacted = tracker.redact({"user_message": "Phone +1 (555) 123-4567"}, fields_to_redact="*")

Encryption

Encryption support has been removed from this SDK.

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

chatsee_ai-0.7.1.tar.gz (10.3 kB view details)

Uploaded Source

Built Distribution

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

chatsee_ai-0.7.1-py3-none-any.whl (11.5 kB view details)

Uploaded Python 3

File details

Details for the file chatsee_ai-0.7.1.tar.gz.

File metadata

  • Download URL: chatsee_ai-0.7.1.tar.gz
  • Upload date:
  • Size: 10.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.0

File hashes

Hashes for chatsee_ai-0.7.1.tar.gz
Algorithm Hash digest
SHA256 52bebcd0c4a9a82d34a7e90b13aaf255a5cd3dfb7c8ad527c882299d5693c0ba
MD5 d3862544d3713d607918886df662184e
BLAKE2b-256 5a19ee62875eb5a0ef78f8d671ad979e00c38b437086cce7deb2af9126fcccc8

See more details on using hashes here.

File details

Details for the file chatsee_ai-0.7.1-py3-none-any.whl.

File metadata

  • Download URL: chatsee_ai-0.7.1-py3-none-any.whl
  • Upload date:
  • Size: 11.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.0

File hashes

Hashes for chatsee_ai-0.7.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a47c8ed5a33568fb0c033211771014e2e141334785dc1d148efde0007fede1d8
MD5 6cf33799d671690d86b2cdfcd98cb40b
BLAKE2b-256 62081d8fe75445923a969400a66d70af3be68ae98834771d0d68b45777e73aa9

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