Leon is an open-source personal assistant who can live on your server.

Last update: Dec 30, 2022

Overview

Leon

Your open-source personal assistant.

Website :: Documentation :: Roadmap :: Contributing :: Story

👋 Introduction

Leon is an open-source personal assistant who can live on your server.

He does stuff when you ask him for.

You can talk to him and he can talk to you. You can also text him and he can also text you. If you want to, Leon can communicate with you by being offline to protect your privacy.

Why?

If you are a developer (or not), you may want to build many things that could help in your daily life. Instead of building a dedicated project for each of those ideas, Leon can help you with his packages/modules (skills) structure.

With this generic structure, everyone can create their own modules and share them with others. Therefore there is only one core (to rule them all).

Leon uses AI concepts, which is cool.

Privacy matters, you can configure Leon to talk with him offline. You can already text with him without any third party services.

Open source is great.

What is this repository for?

This repository contains the following nodes of Leon:

The server

The packages/modules

The web app

The hotword node

What is Leon able to do?

Today, the most interesting part is about his core and the way he can scale up. He is pretty young but can easily scale to have new features (packages/modules). You can find what he is able to do by browsing the packages list.

Sounds good for you? Then let's get started!

☁️ Try with a Single-Click

Gitpod will automatically setup an environment and run an instance for you.

🚀 Getting Started

Prerequisites

Node.js >= 14
npm >= 5
Python >= 3
Pipenv >= 2020.11.15
Supported OSes: Linux, macOS and Windows

To install these prerequisites, you can follow the How To section of the documentation.

Installation

# Clone the repository (stable branch)
git clone -b master https://github.com/leon-ai/leon.git leon
# OR download the latest release at: https://github.com/leon-ai/leon/releases/latest

# Go to the project root
cd leon

# Install
npm install

Usage

# Check the setup went well
npm run check

# Build
npm run build

# Run
npm start

# Go to http://localhost:1337
# Hooray! Leon is running

Docker Installation

# Build
npm run docker:build

# Run
npm run docker:run

# Go to http://localhost:1337
# Hooray! Leon is running

📚 Documentation

For full documentation, visit docs.getleon.ai.

🧭 Roadmap

To know what is going on, follow roadmap.getleon.ai.

❤️ Contributing

If you have an idea for improving Leon, do not hesitate.

Leon needs open source to live, the more modules he has, the more skillful he becomes.

📖 The Story Behind Leon

You'll find a write-up on this blog post.

🔔 Stay Tuned

👨 Author

Louis Grenard (@louistiti_fr)

👍 Sponsors

GrAMATO
_{^{30 USD / month}}

marvinpoo
_{^{10 USD / month}}

You?

You can also contribute by sponsoring Leon.

Please note that I dedicate most of my free time to Leon.

By sponsoring the project you make the project sustainable and faster to develop features.

The focus is not only limited to the activity you see on GitHub but also a lot of thinking about the direction of the project. Which is naturally related to the overall design, architecture, vision, learning process and so on...

📝 License

MIT License

Cheers!

Comments

Python && python3
Bonsoir, c'est difficile de mettre ce léon en place, mais je vais y arriver. J'ai un petit problème avec ce python et python3, léon ne detecte pas mon python3 (lors du check) car sur la derniere version derbian la version 2 est toujours utilisé. (Je ne suis pas un pro de linux). Donc suivant les forums on deconseil de remplacer python2 par python3 par defaut. Pourquoi est-ce que léon ne va pas chercher lui meme sa version lorsque les deux sont installés sur la machine? (c'est un detail, voir au mieux une idee). Bon je pense que je peux laisser python (python2) sur mon systeme et configurer léon pour qu'il utilise python3 a la place. Quel est le finchier de conf a modifier pour faire ca, si c'est possible

.: CHECKING :.

➡ /bin/sh -c node --version ✔ v11.13.0

➡ /bin/sh -c npm --version ✔ 6.7.0

➡ /bin/sh -c pipenv --version ✔ pipenv, version 2018.11.26

➡ /bin/sh -c pipenv --where ✔ /home/odroid/leon

➡ /bin/sh -c pipenv run python --version ✖ The Python version must be 3.6.x. Please install it: https://www.python.org/downloads

➡ /bin/sh -c pipenv run python bridges/python/main.py en leon randomnumber "Give me a random number" ✖ Error: Command failed: /bin/sh -c pipenv run python bridges/python/main.py en leon randomnumber "Give me a random number" Traceback (most recent call last): File "bridges/python/main.py", line 4, in import utils File "/home/odroid/leon/bridges/python/utils.py", line 6, in from pathlib import Path ImportError: No module named pathlib

[email protected]:~$ python --version Python 2.7.15rc1 [email protected]:~$ python3 --version Python 3.6.7

Merci pour ton aide et ton projet que j'ai franchement hâte de tester.
question
opened by marrodeur 24

Leon don't want to talk french, angry omelette du fromage

Specs

Leon version: beta 3
OS (or browser) version: Windows 10 but Leon on WSL Ubuntu 18
Node.js version: 11
Complete "npm run check" output:

---

.: CHECKING :.

➡ /bin/sh -c node --version
✔ v11.15.0

➡ /bin/sh -c npm --version
✔ 6.7.0

➡ /bin/sh -c pipenv --version
✔ pipenv, version 2018.11.26

➡ /bin/sh -c pipenv --where
✔ /home/user/leon-dev/bridges/python

➡ /bin/sh -c pipenv run python --version
✔ Python 3.6.7

➡ /bin/sh -c pipenv run python bridges/python/main.py scripts/assets/query-object.json
✔ {"package": "leon", "module": "randomnumber", "action": "run", "lang": "en", "input": "Give me a random number", "entities": [], "output": {"type": "end", "codes": ["success"], "speech": 8, "options": {}}}

➡ Classifier state
✔ Found and valid

➡ Amazon Polly TTS
❗ Amazon Polly TTS is not yet configured

➡ Google Cloud TTS/STT
❗ Google Cloud TTS/STT is not yet configured

➡ Watson TTS
❗ Watson TTS is not yet configured

➡ Offline TTS
❗ Cannot find bin/flite/flite. You can setup the offline TTS by running: "npm run setup:offline-tts"

➡ Watson STT
❗ Watson STT is not yet configured

➡ Offline STT
❗ Cannot find bin/deepspeech/lm.binary. You can setup the offline STT by running: "npm run setup:offline-stt"

---

.: REPORT :.

➡ Here is the diagnosis about your current setup
✔ Run
✔ Run modules
✔ Reply you by texting
❗ Amazon Polly text-to-speech
❗ Google Cloud text-to-speech
❗ Watson text-to-speech
❗ Offline text-to-speech
❗ Google Cloud speech-to-text
❗ Watson speech-to-text
❗ Offline speech-to-text

✔ Hooray! Leon can run correctly
➡ If you have some yellow warnings, it is all good. It means some entities are not yet configured

Actual Behavior

When i talk whit Leon in french it's crash

How Do We Reproduce?

Talk french with Leon :p

Extra (like a sample repo to reproduce the issue, etc.)

(node:1042) UnhandledPromiseRejectionWarning: TypeError: Cannot read property 'split' of undefined
    at Nlu.process (/home/user/leon-dev/server/dist/core/nlu.js:103:45)
    at processTicksAndRejections (internal/process/task_queues.js:86:5)
(node:1042) UnhandledPromiseRejectionWarning: Unhandled promise rejection. This error originated either by throwing inside of an async function without a catch block, or by rejecting a promise which was not handled with .catch(). (rejection id: 1)
(node:1042) [DEP0018] DeprecationWarning: Unhandled promise rejections are deprecated. In the future, promise rejections that are not handled will terminate the Node.js process with a non-zero exit code.

opened by NT-me 17

Python 3.6

Good morning,

When i launch npm install, i get that : ✖ Error: Command failed: /bin/sh -c pipenv install --skip-lock Warning: Python 3.6 was not found on your system... You can specify specific versions of Python with: $ pipenv --python path/to/python

I am on raspberry 1, raspbian 10
bug

opened by Gadgetroch 15
Leon weather
What type of change does this PR introduce?

[ ] Bugfix

[X] Feature

[ ] Refactor

[ ] Documentation

[ ] Not Sure?

Does this PR introduce breaking changes?

[ ] Yes

[X ] No

Description:

With this package you can ask Leon about the weather in all the cities of the world. It's not full finish because it's miss test and little things.
opened by NT-me 15
How to update the packages?
How can I test my packages?

I am trying to add some modules in the Existing package. I have added the quotes module in the leon package.

I added this inleon/data/expressions/en.json

"quote": [ "Tell me a Quote", "Give me a Quote", ]

Then I have updated the below in ` leon/data/expressions/en.json

"quote":{ "quotes": [ "Design is the silent ambassador of your brand. ", "If there is one word I’d like to remove from any conversation about design, it’s “pretty.", ] }

Then I create a new python file named quote.py. Please see the below code.

import utils def quote(string): """Leon says some quote""" return utils.output('end', 'quotes', utils.translate('quotes'))

I also created a new test python file in the test folder.

But it seems it breaks leon. Wheneve I ask question it gives reply as "Sorry, I don't work correctly!"

How can I test the modules? Do I need to add anything else?
question
opened by menporulporiayalan 15
chore(deps): bump googleapis from 67.1.1 to 89.0.0
Bumps googleapis from 67.1.1 to 89.0.0.

Release notes

Sourced from googleapis's releases.

googleapis googleapis-v89.0.0

⚠ BREAKING CHANGES

retail: This release has breaking changes.

gkehub: This release has breaking changes.

dns: This release has breaking changes.

appengine: This release has breaking changes.

logging: This release has breaking changes.

compute: This release has breaking changes.

paymentsresellersubscription: This release has breaking changes.

bigtableadmin: This release has breaking changes.

Features

analyticsadmin: update the API (983f8ba)

androidpublisher: update the API (2ef419e)

appengine: update the API (70c3733)

area120tables: update the API (d86574a)

artifactregistry: update the API (7de8325)

bigquery: update the API (0de2e24)

bigtableadmin: update the API (8ef0acf)

bigtableadmin: update the API (863c7f0)

chromepolicy: update the API (f6162a3)

cloudbuild: update the API (18fd64a)

cloudsearch: update the API (7c220ea)

compute: update the API (30bea18)

container: update the API (ab6d3f7)

content: update the API (3e942b4)

dialogflow: update the API (6495352)

dns: update the API (5fb88d6)

documentai: update the API (58576db)

domains: update the API (ba89daa)

firebase: update the API (9629195)

gkehub: update the API (7c7f873)

healthcare: update the API (33297c0)

iap: update the API (b95fd46)

localservices: update the API (43de21d)

logging: update the API (733a33b)

managedidentities: update the API (4904a02)

monitoring: update the API (7509670)

networkservices: update the API (339e0d3)

osconfig: update the API (2ff13e6)

osconfig: update the API (a2c067c)

paymentsresellersubscription: update the API (6564211)

realtimebidding: update the API (8bd83cf)

redis: update the API (6821f71)

regenerate index files (1a615ed)

regenerate index files (81d5df4)

... (truncated)

Changelog

Sourced from googleapis's changelog.

89.0.0 (2021-10-18)

⚠ BREAKING CHANGES

retail: This release has breaking changes.

gkehub: This release has breaking changes.

dns: This release has breaking changes.

appengine: This release has breaking changes.

logging: This release has breaking changes.

compute: This release has breaking changes.

paymentsresellersubscription: This release has breaking changes.

bigtableadmin: This release has breaking changes.

Features

analyticsadmin: update the API (983f8ba)

androidpublisher: update the API (2ef419e)

appengine: update the API (70c3733)

area120tables: update the API (d86574a)

artifactregistry: update the API (7de8325)

bigquery: update the API (0de2e24)

bigtableadmin: update the API (8ef0acf)

bigtableadmin: update the API (863c7f0)

chromepolicy: update the API (f6162a3)

cloudbuild: update the API (18fd64a)

cloudsearch: update the API (7c220ea)

compute: update the API (30bea18)

container: update the API (ab6d3f7)

content: update the API (3e942b4)

dialogflow: update the API (6495352)

dns: update the API (5fb88d6)

documentai: update the API (58576db)

domains: update the API (ba89daa)

firebase: update the API (9629195)

gkehub: update the API (7c7f873)

healthcare: update the API (33297c0)

iap: update the API (b95fd46)

localservices: update the API (43de21d)

logging: update the API (733a33b)

managedidentities: update the API (4904a02)

monitoring: update the API (7509670)

networkservices: update the API (339e0d3)

osconfig: update the API (2ff13e6)

osconfig: update the API (a2c067c)

paymentsresellersubscription: update the API (6564211)

realtimebidding: update the API (8bd83cf)

redis: update the API (6821f71)

regenerate index files (1a615ed)

regenerate index files (81d5df4)

... (truncated)

Commits

2d1e152 chore: release main (#2812)

29ea4a1 build(node): update deps used during postprocessing (#1243) (#2817)

1a615ed feat: regenerate index files

4ab24ee fix(vmmigration): update the API

42db7be fix(versionhistory): update the API

2559495 fix(streetviewpublish): update the API

64dedce feat(speech): update the API

6ae8dd3 fix(sourcerepo): update the API

276ebcf feat(servicenetworking): update the API

7e40942 fix(servicemanagement): update the API

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

dependencies
opened by dependabot[bot] 14
chore(deps): bump @google-cloud/text-to-speech from 3.2.1 to 3.3.1
Bumps @google-cloud/text-to-speech from 3.2.1 to 3.3.1.

Release notes

Sourced from @google-cloud/text-to-speech's releases.

@google-cloud/text-to-speech v3.3.1

Bug Fixes

build: set default branch to main (#548) (6891351)

@google-cloud/text-to-speech v3.3.0

Features

turns on self-signed JWT feature flag (#543) (bd5ecd3)

@google-cloud/text-to-speech v3.2.7

Bug Fixes

deps: google-gax v2.24.1 (#541) (0c93b5b)

@google-cloud/text-to-speech v3.2.6

Bug Fixes

Updating WORKSPACE files to use the newest version of the Typescript generator. (#534) (dee8dc2)

v3.2.5

Bug Fixes

deps: google-gax v2.17.1 (#532) (200ddae)

v3.2.4

Bug Fixes

deps: google-gax v2.17.0 with mTLS (#529) (5c6c68c)

v3.2.3

Bug Fixes

make request optional in all cases (#525) (256f21b)

v3.2.2

Bug Fixes

GoogleAdsError missing using generator version after 1.3.0 (#515) (f48e238)

Changelog

Sourced from @google-cloud/text-to-speech's changelog.

3.3.1 (2021-09-10)

Bug Fixes

build: set default branch to main (#548) (6891351)

3.3.0 (2021-08-23)

Features

turns on self-signed JWT feature flag (#543) (bd5ecd3)

3.2.7 (2021-08-17)

Bug Fixes

deps: google-gax v2.24.1 (#541) (0c93b5b)

3.2.6 (2021-07-21)

Bug Fixes

Updating WORKSPACE files to use the newest version of the Typescript generator. (#534) (dee8dc2)

3.2.5 (2021-07-12)

Bug Fixes

deps: google-gax v2.17.1 (#532) (200ddae)

3.2.4 (2021-06-30)

Bug Fixes

deps: google-gax v2.17.0 with mTLS (#529) (5c6c68c)

3.2.3 (2021-06-23)

Bug Fixes

make request optional in all cases (#525) (256f21b)

3.2.2 (2021-06-04)

... (truncated)

Commits

7548220 chore: release 3.3.1 (#549)

6891351 fix(build): set default branch to main (#548)

3cfc7ea chore: disable renovate dependency dashboard (#1194) (#546)

a9cf8a5 chore: release 3.3.0 (#544)

bd5ecd3 feat: turns on self-signed JWT feature flag (#543)

d4564e7 chore: release 3.2.7 (#542)

0c93b5b fix(deps): google-gax v2.24.1 (#541)

f401556 build: update auto-approve config for new validation (#1169) (#538)

99a820d chore: release 3.2.6 (#535)

359136d build: switch to release-please release tagging (#1129) (#537)

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

dependencies
opened by dependabot[bot] 14
Docker Install - no modules seems working v2019-03-04

Hello,

I create this issue but the problem can be on my side ;), I install Leon on my ArchLinux with docker, The build and installation looks good, leon start on Leet's port ;) so when I want to speak with leon It looks like no modules work as we see on the screen capture :) I think the problem can be on my side, I have archLinux with deepin and docker don't have the reputaton to work good on it :P, I create this issue because if an other person have the same problem as me He can add it to this issue ;) Don't see it as a big priority, I have a lot of time to see what you do ;) My english is not perfect as you can see, I speak better french than English but I work on ;)

Have a Nice day and be happy !!!!
bug

opened by rioukkevin 12
Unable to install it in ubuntu 18.10
Specs

Leon version: commit d0ca87d

pipenv version - 2018.11.26

npm version - 5.8.0

python version - 3.6.7

OS - Ubuntu 18.10

Expected Behaviour Leon Should build successfully

Actual Behaviour Throwed an error While installing the python package

Error Message ✖ Failed to install the Python packages: Error: Command failed: /bin/sh -c pipenv install

Any help would be appreciated.
question
opened by menporulporiayalan 12
Docker image added
What type of change does this PR introduce?

[ ] Bugfix

[X] Feature

[ ] Refactor

[X] Documentation

[ ] Not Sure?

Does this PR introduce breaking changes?

[ ] Yes

[X] No

List any relevant issue numbers:

https://github.com/leon-ai/leon/issues/1 https://github.com/leon-ai/leon/issues/4

Description:

I added a DockerImage to run Leon, I also detailed the steps in the readme.md

Unfortunately I saw the leon-ci-images afterward so my image is a bit different (so could be refactored)
opened by Antoinebr 12
Improve NLU for more detailed queries

Be able to subtract a type of entity from a query. Such as date, number, location, etc.

If it uses a tiers but Node.js, it should operate from the core and send the result object to modules via the child process parameters. Otherwise, it should fully be implemented in the core itself.

I noted some following leads in this Trello card.
improvement

opened by louistiti 12

Releases(tcp-server_v1.0.0)

tcp-server_v1.0.0(Oct 22, 2022)

Leon's TCP server to communicate between the core and third-party nodes.
Source code(tar.gz)
Source code(zip)
leon-tcp-server-linux-aarch64.zip(622.19 MB)
leon-tcp-server-linux-x86_64.zip(1346.21 MB)
leon-tcp-server-macosx-arm64.zip(642.84 MB)
leon-tcp-server-macosx-x86_64.zip(838.10 MB)
leon-tcp-server-win-amd64.zip(732.08 MB)
python-bridge_v1.0.0(Oct 22, 2022)

Leon's Python bridge to communicate between the core and skills made with Python.
Source code(tar.gz)
Source code(zip)
leon-python-bridge-linux-aarch64.zip(11.18 MB)
leon-python-bridge-linux-x86_64.zip(12.65 MB)
leon-python-bridge-macosx-arm64.zip(9.23 MB)
leon-python-bridge-macosx-x86_64.zip(10.50 MB)
leon-python-bridge-win-amd64.zip(14.99 MB)
v1.0.0-beta.7(Aug 24, 2022)
Please read this blog post to know more about all the new features and the exciting future of Leon.

BREAKING CHANGES

remove legacy packages 07743657

Features

create new NLP skills resolvers model + NLP global resolvers model 602604e4

better isolate skill resolvers from global resolvers + finish up Akinator skill 905d248e

transfer language from core to skills + support thematics on Akinator skill b35a249b

actions on slot level + akinator skill progress 7101b8b4

add Cartesian sample training on resolvers + enum entities 6ed88a59

map skills resolvers intents eb5ade76

train skills resolvers and remap as per changes 82df0a3c

achieve Cartesian training a1e9011d

introduce suggestions dcddacca

communicate suggestions to the client 4b5a8835

shared skills memory 795acc5b

support dynamic variables on skill NLU settings for logic type 10d10a16

tmp resolvers mapping b1a332ba

start to map resolvers between the core and skills e88495a9

train affirmation and denial resolver 993d52e8

Python TCP server and Node.js TCP client for IPC (wip) 5970ec9e

introduce spaCy for complete NER (wip) caa86fc8

slot filling (wip) 76547d94

share data across domains f4f9fff9

dynamic variable binding on NLG 0367b44f

context and slot filling preparation (wip) 975b8ebc

annotate entities on the fly + prepare for dialog skill type and cross-domains data 4107932d

new NLP training d8023308

server:

trigger next action suggestions or current ones 244d08c0

introduce main NLP model and resolvers NLP model e37526d9

change log emojis 843bc428

provide nextAction even when no slot is set and clean up NLU object on context switch 8377c63d

report full traceback from skills execution b69b1fea

support on-the-fly entity annotation for built-in entities 567b030c

save slots within conversation context fce47cdb

resolve resolvers tmp ceea47ff

prepare the next action on non-slot-filled skills 0acb31a9

add more affirmative utterance samples 870ab2e8

restart a skill with the original utterance saved in context f4446ef1

clean up context if the action loop does not meet the expected items 035c9d52

add handsigns custom entity 1529c720

reprocess NLU in case of slot filling interruption 9e242d77

handle action loop when slots have all been filled at once f8830502

break the action loop from the skill 27dc801c

stop action loop from skill to core 99681e25

introduce basic concept of action loop c5b38400

prepare action loop feature 19e1aa22

add current utterance entities to differentiate from the whole context 8b56a185

when a context is activated, pick up the most probable classification 8e186879

persist entities into contexts 87575773

forward slots to skill + add original utterance 68e40f65

handle case when all slots have been filled in one utterance 22e9234b

trigger next action once all slots have been filled 9b870010

complete slot filling before triggering the next action 9124687e

from modules to skills with type at the actions level 77ebaf4a

verify if all slots are filled e27c1b9c

context and slot filling, keep context and await for entities 25adf406

unstack oldest context 1ece25a4

context setup with slot for each conversation (wip) 8257eb87

resolve slots from slot filling 960a6dc7

pickup questions for slot filling 3bbc2f8a

main slots structure (wip) 1d9b1809

introduce resolvers for slot filling (wip) 334bf393

slot filling PoC (tmp wip) 95bfcfe4

slot filling (wip) 969a83e6

trigger unsupported language 1845eed7

context (wip) d1c2a11d

context (wip) a9a43ac4

differenciate cities from countries for location entities bf9bf231

auto restart the TCP server when language is switching 9be7c700

support multi languages on TCP server a808742c

add auto reconnect on TCP client cbe89ed6

make TCP client global 006e9fb0

fully implement low-level networking for IPC 8acb82da

more accurate NLG d5577b1e

unknown_answers fallback on dialog type 28efe6e7

deep data mapping on enum NER 3ca48265

NLG and entities mapping 8f2f935b

bootstrap skill structure fe90c68e

on-the-fly language switching f24513a2

new NLP containers 34b2aa56

(WIP) NLU refactoring ca3f5f42

add skills domains cf2a28aa

skill/akinator:

finish up 79e7df02

finished main business logic 76cae42f

backbone 02a2f714

skill/birthday: remove birthday skill be0b345d

skill/color: introduce color skill ce00989b

skill/guess_the_number: introduce the Guess the Number skill fba80966

skill/introduction:

add one utterance sample af0fdd1e

ask about owner info if necessary c5cc9bdd

skill/mbti:

complete form resolver aad9f3f1

finish business logic 99a3f103

questions mapping ae4f69f7

complete questionnaire 7f1f8871

main logic backbone 33109a4c

main NLU structure [skip ci] 86d5040a

skill/rochambeau:

add start answers 192dd0a8

introduce paper scissors rock 57370470

init 7f5e30ac

web app:

join us on Discord 141c89ec

wait for TCP client to be connected first bc228a68

Bug Fixes

check script with new intent-object format fdf0a389

check new resolvers paths cfd8f7cb

use ports.ubuntu.com mirror for the offline TTS [skip ci] 3dd90396

set skill config only when a bridge is set 7513aa7d

only set skill config when it is a logic type 9ce9a8bc

docker:

usage of Ubuntu base image with pyenv and nvm (#408) f507f6f7

check should not allocate a pseudo-TTY (#359) 4372b45f

server:

make leon handle multiple socket.io-client instances 6e7c0aac

fallback on global resolver during resolver classification ec77dd0f

make use of current entities to match global entities a8d82050

multiple slots filling 2ac1bc63

context switching on action loop 6712ae55

check one-shot slot filling case causing infinite loop 782a3aaa

clean up active context after all slots have been filled faabc2c7

correctly extract all spaCy entities 6aa60bfb

intent not found 8280c658

fallback due to modules to skills refactoring ef0c54b2

NER due to modules to skills refactoring e4d3904c

skill/akinator: remove direct end on guess action f6461f73

skill/color: more appropriate answer cb18ed63

skill/rochambeau: final logic 0ebc0518

Performance Improvements

check Pipfile instead of Pipfile.lock to judge whether Python packages must be installed afdb71f7

Documentation Changes

change newsletter link 4bf2a9af

README - Edited sentence for clarity (#389) e83a1c42

edit newsletter link fa558a44

update sponsor [skip ci] f30ddb6b

remove sponsor [skip ci] 5dbc010f

remove sponsor [skip ci] f36dd20f

remove sponsor [skip ci] 5ee57ddf

add @ant-media sponsor [skip ci] b47cbc3a

add long dev notice to README [skip ci] 499be77d

move sponsor to new section [skip ci] 8825d687

change Twitter handle [skip ci] c1afc11c

remove sponsor [skip ci] 99b401a6

add new sponsor self-hosted img [skip ci] 238d928c

remove new sponsor link (broken) [skip ci] 254f2848

in GitHub BUG.md from modules to skills 4a5480a3

change @FluxIndustries sponsorship [skip ci] 1a118b71

add @FluxIndustries sponsor [skip ci] 9a604d7c

new #LeonAI link [skip ci] a0107d62

changelog new version diff link fix [skip ci] e14c2498

Source code(tar.gz)
Source code(zip)
v1.0.0-beta.6(Feb 7, 2022)
Features

simple coqui-ai stt integration 86a4816b @johannbarbie

HTTP API key generator d10a7fa7

avoid unnecessary routes generation

server:

make Coqui STT the default STT solution 70399187

add HTTP API key middleware cdf41499

expose queries over HTTP b6428d03

add timeout action over HTTP 115f9c16

handle built-in and trim entities over HTTP + add "disabled" HTTP API action option 82fb967a

execute modules over HTTP 2e5b2c59

generate Fastify routes on the file to expose packages over HTTP 5b41713a

Bug Fixes

do not ask to regenerate the HTTP API key if this one isn't available yet d265377a

Python deps tree check c6c01291

hotword offline (#342) f563d01d

addressed comments by @JRMeyer b1c6f5c8

allow to detect STT offline capabilities 04d62288

Amazon Polly is always configured on check script due to new structure e6246d1f

Performance Improvements

check if Python deps tree has been updated before going through deps install 2d0b0f13

Source code(tar.gz)
Source code(zip)
v1.0.0-beta.5(Dec 28, 2021)
This release marks a major turn in the future versions of the Leon core. Please read this blog post to know more.

BREAKING CHANGES

Node.js 16+ and npm 8+ minimum requirements 2f66f1c1

Features

server: support arrays on NER between conditions 7cf7f979

Bug Fixes

jest-extended new setup due to latest update 02f766d6

Performance Improvements

Windows setup on DeepSpeech dep removal 13f5a49f

Documentation Changes

URL redirect managed by registrar c16d5b28

Source code(tar.gz)
Source code(zip)
v1.0.0-beta.4(May 1, 2021)
This release includes a lot of changes that are made under the hood and are not displayed here, please read the blog post to know more.

BREAKING CHANGES

package/checker: introduce Have I Been Pwned v3 API with API key (0ca89fe3)

server:

AWS SDK new structure due to v3 and adapt Amazon Polly changes (f15f2db7)

IBM Watson TTS and STT new structure (f41ea0e9 | 2668c295)

Features

package/calendar: introduce To-Do list module (0cdd73d6 | 857be947 | 2041be14 | 12e8f5c3 | 8575e9e3 | 5e128df0 | 602aa694 | b9693df9 | 581da8cd | 53f7db55 | ae073971)

package/checker: introduce Have I Been Pwned module (61c1b55a | 5a999bc6 | 36368664 | a7a6d885 | c73ba52b | 8374e548 | a476fd0f)

package/network: add speedtest module (09ad4340)

server:

add regex entity type 3fda3526

catch unsupported action entity type 5bc6c3f1

NER backbone 24cf3c9a

introduce actions module b449376f

Bug Fixes

set correct status code for GET /downloads 690f1841

take .env in consideration when using Docker d38e6095

spinner test 9071c927

e2e tests by adding modules actions level 5cf77d90

package/leon: fix english translations 90225707

package/network: make use of new compatible speedtest lib 0c925626

package/trend:

GitHub module new scraping 68414937

when there is no star provided on the GitHub module 563fb409

server:

make use of Basic plugin from the main NLP container e1d5bed3

NER trim entity on after conditions fa6a5a43

Documentation Changes

add minimum Pipenv version requirement to README 72e46bd6

hunt broken links b2a22792

add "ci" commit type in CONTRIBUTING.md 09e2672b

use emojies in README 0ea7a78b

add social badges to README c55c7532

Node.js 14 requirement d1034bd1

Source code(tar.gz)
Source code(zip)
1.0.0-beta.2(Apr 23, 2019)
Features

can send custom HTTP headers (2685cdab)

allow HTML output (ec3f02df)

NLU improvement with node-nlp (6585db71)

package/trend:

add answer when the Product Hunt developer token is not provided (f40b479b)

Product Hunt module done (37794306)

basics done on the Product Hunt module (32cc7dbe)

complete dedicated answers according to the technology and given time (8997d691)

GitHub module done (7c6f3922)

be able to choose a limit and a date range for the GitHub module (3c088371)

format GitHub results in one message (9d026b94)

simple GitHub module results (5baec074)

list GitHub trends in HTML raw (3441629e | 6b932e94)

expressions dataset and structure (f406a5a0 | f54c2272)

Bug Fixes

Leon was not fully installed with Docker if a .env file was existing (c8a68ab0)

package/trend: when there is no contributor on GitHub module (d845e49b)

server:

skip Pipenv locking until they fix it (029381e3 | ecfdc73f)

Documentation Changes

add What is Leon able to do? section in the readme (87f53c91 | d558fc8b)

open-source != open source (16a9372e | 2155cd88)

Source code(tar.gz)
Source code(zip)
1.0.0-beta.1(Feb 24, 2019)
Features

add Docker support (209760db)

Bug Fixes

package/checker: isitdown module fails with capital letters in URL (ada6aaef)

web app: enable environment variables (a438d6f9)

Performance Improvements

web app: favicon compression (33dbcb42)

Documentation Changes

update README to make the reader genderless (58662658)

use "to rule them all" in README (c74dda4c)

readme: add story write-up (08a68e37)

Source code(tar.gz)
Source code(zip)
1.0.0-beta.0(Feb 10, 2019)

First release. See more on https://docs.getleon.ai.
Source code(tar.gz)
Source code(zip)

Owner

Leon AI

Open-Source Personal Assistant.

GitHub Repository https://getleon.ai

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

PaddleNLP 2.0拥有丰富的模型库、简洁易用的API与高性能的分布式训练的能力，旨在为飞桨开发者提升文本建模效率，并提供基于PaddlePaddle 2.0的NLP领域最佳实践。

6.9k Jan 01, 2023

中文无监督SimCSE Pytorch实现

A PyTorch implementation of unsupervised SimCSE SimCSE: Simple Contrastive Learning of Sentence Embeddings 1. 用法无监督训练 python train_unsup.py ./data/ne

99 Dec 23, 2022

Python bindings to the dutch NLP tool Frog (pos tagger, lemmatiser, NER tagger, morphological analysis, shallow parser, dependency parser)

Frog for Python This is a Python binding to the Natural Language Processing suite Frog. Frog is intended for Dutch and performs part-of-speech tagging

46 Dec 14, 2022

A benchmark for evaluation and comparison of various NLP tasks in Persian language.

Persian NLP Benchmark The repository aims to track existing natural language processing models and evaluate their performance on well-known datasets.

68 Dec 19, 2022

End-to-End Speech Processing Toolkit

ESPnet: end-to-end speech processing toolkit system/pytorch ver. 1.0.1 1.1.0 1.2.0 1.3.1 1.4.0 1.5.1 1.6.0 1.7.1 1.8.1 ubuntu18/python3.8/pip ubuntu18

5.9k Jan 03, 2023

Transformers-regression - Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates

Regression Free Model Update Code for the paper: Regression Bugs Are In Your Mod

2 Feb 17, 2022

Simplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code

simple_diarizer Simplified diarization pipeline using some pretrained models. Made to be a simple as possible to go from an input audio file to diariz

65 Dec 30, 2022

Python library for processing Chinese text

SnowNLP: Simplified Chinese Text Processing SnowNLP是一个python写的类库，可以方便的处理中文文本内容，是受到了TextBlob的启发而写的，由于现在大部分的自然语言处理库基本都是针对英文的，于是写了一个方便处理中文的类库，并且和TextBlob

6k Jan 02, 2023

A natural language modeling framework based on PyTorch

Overview PyText is a deep-learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapi

6.4k Jan 08, 2023

Pipelines de datos, 2021.

Este repo ilustra un proceso sencillo de automatización de transformación y modelado de datos, a través de un pipeline utilizando Luigi. Stack princip

8 May 19, 2022

NLP: SLU tagging

3 Jan 14, 2022

Findings of ACL 2021

Assessing Dialogue Systems with Distribution Distances [arXiv][code] We propose to measure the performance of a dialogue system by computing the distr

16 Feb 24, 2022

Th2En & Th2Zh: The large-scale datasets for Thai text cross-lingual summarization

Th2En & Th2Zh: The large-scale datasets for Thai text cross-lingual summarization 📥 Download Datasets 📥 Download Trained Models INTRODUCTION TH2ZH (

5 Jan 03, 2022

Sentello is python script that simulates the anti-evasion and anti-analysis techniques used by malware.

sentello Sentello is a python script that simulates the anti-evasion and anti-analysis techniques used by malware. For techniques that are difficult t

62 Oct 02, 2022

Code for papers "Generation-Augmented Retrieval for Open-Domain Question Answering" and "Reader-Guided Passage Reranking for Open-Domain Question Answering", ACL 2021

This repo provides the code of the following papers: (GAR) "Generation-Augmented Retrieval for Open-domain Question Answering", ACL 2021 (RIDER) "Read

49 Dec 26, 2022

Leon is an open-source personal assistant who can live on your server.

Related tags

Overview

Leon

👋 Introduction

Why?

What is this repository for?

What is Leon able to do?

☁️ Try with a Single-Click

🚀 Getting Started

Prerequisites

Installation

Usage

Docker Installation

📚 Documentation

🧭 Roadmap

❤️ Contributing

📖 The Story Behind Leon

🔔 Stay Tuned

👨 Author

👍 Sponsors

📝 License

Cheers!

Comments

Specs

Actual Behavior

How Do We Reproduce?

Extra (like a sample repo to reproduce the issue, etc.)

What type of change does this PR introduce?

Does this PR introduce breaking changes?

Description:

How can I test my packages?

googleapis googleapis-v89.0.0

⚠ BREAKING CHANGES

Features

89.0.0 (2021-10-18)

⚠ BREAKING CHANGES

Features

@​google-cloud/text-to-speech v3.3.1

Bug Fixes

@​google-cloud/text-to-speech v3.3.0

Features

@​google-cloud/text-to-speech v3.2.7

Bug Fixes

@​google-cloud/text-to-speech v3.2.6

Bug Fixes

v3.2.5

Bug Fixes

v3.2.4

Bug Fixes

v3.2.3

Bug Fixes

v3.2.2

Bug Fixes

3.3.1 (2021-09-10)

Bug Fixes

3.3.0 (2021-08-23)

Features

3.2.7 (2021-08-17)

Bug Fixes

3.2.6 (2021-07-21)

Bug Fixes

3.2.5 (2021-07-12)

Bug Fixes

3.2.4 (2021-06-30)

Bug Fixes

3.2.3 (2021-06-23)

Bug Fixes

3.2.2 (2021-06-04)

What type of change does this PR introduce?

Does this PR introduce breaking changes?

List any relevant issue numbers:

Description:

Releases(tcp-server_v1.0.0)

tcp-server_v1.0.0(Oct 22, 2022)

python-bridge_v1.0.0(Oct 22, 2022)

v1.0.0-beta.7(Aug 24, 2022)

BREAKING CHANGES

Features

Bug Fixes

`@google-cloud/text-to-speech` v3.3.1

`@google-cloud/text-to-speech` v3.3.0

`@google-cloud/text-to-speech` v3.2.7

`@google-cloud/text-to-speech` v3.2.6