Skip to main content

datapaw-cli

Standalone command-line interface for DataPaw.

This package provides the datapaw command and connects local host workflows through datapaw-host-core.

The command automatically loads DATAPAW_ENV_FILE when set. Otherwise, an editable checkout is discovered from the CLI package location and the repository root .env is loaded. Existing process environment variables take precedence over dotenv values. Outside an editable checkout, the current working directory is used as the fallback configuration root.

Available command groups:

  • plan
  • execute
  • run
  • chat
  • datasource list
  • doctor

Run datapaw doctor before the first task to check supported Python/Node versions, uv, model and authentication configuration, DataPaw Home, DataBridge MCP, Docker, Neo4j, and the DataBridge API. datapaw doctor --json emits a machine-readable report that reports whether credentials are set without printing their values.

datasource list reads every datasource configured in DataBridge:

datapaw datasource list

Set DATAPAW_CM_BASE_URL to the DataBridge origin. It defaults to http://127.0.0.1:8765. The command emits JSON and masks saved passwords, AccessKeys, and STS tokens before writing anything to stdout.

The default CLI model uses provider openai together with LLM_MODEL, OPENAI_API_KEY, and OPENAI_BASE_URL. Set the corresponding DATAPAW_MODEL_PROVIDER, DATAPAW_MODEL_NAME, DATAPAW_MODEL_API_KEY, and DATAPAW_MODEL_BASE_URL variables to override individual values for the CLI.

Output and logs

The CLI writes streamed agent events, final answers, and execution summaries to stdout. Interactive prompts and concise command errors remain explicit CLI output on the terminal rather than raw log records. Python logging is written to ${DATAPAW_HOME}/host/datapaw.log at INFO level and above; DATAPAW_HOME defaults to ~/.datapaw.

The log rotates at 50 MB and keeps two backups as datapaw.log.1 and datapaw.log.2. Rotation assumes one active CLI process per DATAPAW_HOME. Direct users of datapaw-host-core continue to own their process logging configuration.

This package intentionally omits serve and local initialization helpers from the public CLI help.

Download files

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

Source Distribution

datapaw_cli-0.1.0.tar.gz (25.8 kB view details)

Uploaded Source

Built Distribution

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

datapaw_cli-0.1.0-py3-none-any.whl (24.5 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: datapaw_cli-0.1.0.tar.gz
  • Upload date:
  • Size: 25.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for datapaw_cli-0.1.0.tar.gz
Algorithm Hash digest
SHA256 95899c1269ea81b31742a3376958d24729e1dcf32a351567b23f65564f9e78eb
MD5 10ed2cb756f9e9fe97c8b43921c1b476
BLAKE2b-256 a27a1a2baf14e4d7ad1abc8273a3d6dfb2315b9374a3ecffa37eb558685ddaee

See more details on using hashes here.

File details

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

File metadata

  • Download URL: datapaw_cli-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 24.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for datapaw_cli-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5eff1795092fd2bb5490cc736babd7edaafbb5ee62287f3708ffe026e435ca45
MD5 0a983850dc6d97f76a9d4f61a8becc76
BLAKE2b-256 3711b666536c0c7c2aae9fb42ee9d2a74b1d462f152d3c706c98924cd0e781ae

See more details on using hashes here.

Release history Release notifications | RSS feed

0.2.4

2 files

0.2.0

2 files

0.1.2

2 files

0.1.1

2 files

This release

0.1.0 This release

2 files

Supported by

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