A framework for rapidly building large-scale, deterministic, interactive workflows with a fault-tolerant, conversational UX

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for drawal1 from gravatar.com drawal1

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: Apache Software License (Apache-2.0)
  • Author: Dhar Rawal
  • Tags fastworkflow , ai , workflow , llm , openai
  • Requires: Python <3.13, >=3.11
Classifiers
Report project as malware

Project description

fastWorkflow

A framework for rapidly building large-scale, deterministic, interactive workflows with a fault-tolerant, conversational UX and AI-powered recommendations.

  • Built on the principle on "Convention over configuration", ALA Ruby on Rails
  • Uses:
    • A custom-built intent detection pipeline for fault-tolerant, self-correcting command routing
    • Pydantic and DSPy for parameter extraction and response generation

Concepts

  • Workflows are defined as a directory hierarchy of workitem types
    • Workitems can be ordered
    • Min/max constraints can be defined for the number of child workitems (one, unlimited, min/max)
    • Workflows can delegate to other workflows
  • Commands are exposed for each workitem type
    • Commands may be specific to one workitem type or inheritable by child workitem types (base commands)
  • Users are guided through the workflow but have complete control over navigation
    • Workflow navigation and command execution are exposed via a chat interface
    • Special constrained workflows are used to handle routing and parameter extraction errors
  • AI-powered recommendations after every command interaction
    • Recommendations are generated AFTER a command has been processed. The user has complete control over the workflow and discretion over whether to follow a recommendation or take a different action.

Getting started

  • Clone the repo
    • Use WSL if you are on Windows
  • Create a .env file in the passwords folder and add below keys if required
    • LITELLM_API_KEY_SYNDATA_GEN
    • LITELLM_API_KEY_PARAM_EXTRACTION
    • LITELLM_API_KEY_RESPONSE_GEN
    • LITELLM_API_KEY_AGENT
  • Train fastworkflow, then train the sample workflow, finally run the sample workflow agent or assistant
    • Hint: review the .vscode/launch.json file for training/running the sample workflow

Future Roadmap

  • AI enabled python applications
  • Tools to enable rapid application development - declarative/imperative/visual

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for drawal1 from gravatar.com drawal1

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: Apache Software License (Apache-2.0)
  • Author: Dhar Rawal
  • Tags fastworkflow , ai , workflow , llm , openai
  • Requires: Python <3.13, >=3.11
Classifiers

Release history Release notifications | RSS feed

2.17.35

2.17.34

2.17.33

2.17.32

2.17.31

2.17.30

2.17.29

2.17.28

2.17.27

2.17.26

2.17.25

2.17.24

2.17.22

2.17.21

2.17.20

2.17.19

2.17.18

2.17.17

2.17.16

2.17.15

2.17.14

2.17.13

2.17.12

2.17.11

2.17.10

2.17.9

2.17.8

2.17.7

2.17.6

2.17.5

2.17.4

2.17.3

2.17.2

2.17.1

2.17.0

2.16.0

2.15.13

2.15.12

2.15.11

2.15.10

2.15.9

2.15.8

2.15.7

2.15.6

2.15.5

2.15.4

2.15.3

2.15.2

2.15.1

2.15.0

2.14.3

2.14.2

2.14.1

2.14.0

2.13.5

2.13.4

2.13.3

2.13.1

2.13.0

2.12.1

2.12.0

2.11.0

2.10.0

2.9.1

2.9.0

2.8.32

2.8.31

2.8.30

2.8.29

2.8.28

2.8.27

2.8.26

2.8.25

2.8.24

2.8.23

2.8.22

2.8.21

2.8.20

2.8.19

2.8.18

2.8.17

2.8.16

2.8.15

2.8.14

2.8.13

2.8.12

2.8.11

2.8.10

2.8.9

2.8.8

2.8.7

2.8.6

2.8.5

2.8.4

2.8.3

2.8.2

2.8.1

2.8.0

2.7.4

2.7.3

2.7.2

2.7.1

2.7.0

2.6.0

2.5.2

2.5.1

2.0.1

2.0.0

1.4.11

1.4.10

1.4.9

1.4.8

1.4.7

1.4.6

This version

1.4.5

1.4.4

1.4.3

1.4.2

1.4.1

1.4.0

1.3.0

1.2.2

1.2.1

1.2.0

1.1.13

1.1.12

1.1.11

1.1.10

1.1.9

1.1.8

1.1.7

1.1.6

1.1.5

1.1.4

1.1.3

1.1.2

1.1.1

1.1.0

1.0.28

1.0.27

Download files

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

Source Distribution

fastworkflow-1.4.5.tar.gz (71.5 kB view details)

Uploaded Source

Built Distribution

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

fastworkflow-1.4.5-py3-none-any.whl (97.5 kB view details)

Uploaded Python 3

File details

Details for the file fastworkflow-1.4.5.tar.gz.

File metadata

  • Download URL: fastworkflow-1.4.5.tar.gz
  • Upload date:
  • Size: 71.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.2 Linux/6.6.87.1-microsoft-standard-WSL2

File hashes

Hashes for fastworkflow-1.4.5.tar.gz
Algorithm Hash digest
SHA256 e8a48bab739554f08f29d8c105ced999944080b2b4119af3ca99f2e97033031e
MD5 9f0582cdb8798fc5e5bf321edf0e62f1
BLAKE2b-256 62f39e23fedf0b97ec5bf5f5452e3feb78e831180664d44911ff7d384c73eeab

See more details on using hashes here.

File details

Details for the file fastworkflow-1.4.5-py3-none-any.whl.

File metadata

  • Download URL: fastworkflow-1.4.5-py3-none-any.whl
  • Upload date:
  • Size: 97.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.2 Linux/6.6.87.1-microsoft-standard-WSL2

File hashes

Hashes for fastworkflow-1.4.5-py3-none-any.whl
Algorithm Hash digest
SHA256 349f3063a61ff20c12a4904973cb2c10ad82c6f89599f83bb8178deec7ca0699
MD5 2e67837773edc4d1423cf4c76e6e008b
BLAKE2b-256 d23244246d211c87ddbb03d4d4170ae29bad5371b9ab1361b3e6737760eab77b

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