Examples merged into main repo #286
Conversation
|
@ruthenian8 |
examples/frequently_asked_question_bot/telegram/bot/requirements.txt
Outdated
Show resolved
Hide resolved
examples/frequently_asked_question_bot/telegram/bot/pipeline_services/pre_services.py
Outdated
Show resolved
Hide resolved
examples/frequently_asked_question_bot/web/web/bot/pipeline_services/pre_services.py
Outdated
Show resolved
Hide resolved
examples/frequently_asked_question_bot/web/web/requirements.txt
Outdated
Show resolved
Hide resolved
examples/frequently_asked_question_bot/web/web/requirements.txt
Outdated
Show resolved
Hide resolved
|
I think we should change FAQ demo from answering questions about arch linux to answering questions about dff / deeppavlov. That way we could simultaneously teach users something about us or even use this bot in a production environment (e.g. as a helper in df designer). Also, something to consider: we could make the FAQ bot multilingual (it would detect the language of the question and answer in the same language). That could be an interesting feature to showcase our users. |
|
ToDo:
|
| This bot is designed to answer any type of user questions in a limited business domain (book shop). | ||
| Uses a Telegram interface. | ||
|
|
||
| You can read more about deploying the project in its README file. |
There was a problem hiding this comment.
Link to readme file?
|
|
||
| * The rest of the project-related Python code is factored out into other packages. | ||
|
|
||
| * We also create 'run.py' and 'test.py' at the project root. These files import the ready pipeline |
There was a problem hiding this comment.
Link to the files?
| FAQ bot for Deeppavlov users built using `DFF`. | ||
| Can be run with Telegram or with a web interface. | ||
|
|
||
| You can read more about deploying the project in its README file. |
There was a problem hiding this comment.
Link to the readme file?
| The API responds with a nested array containing `label - score` pairs. | ||
|
|
||
| ```json | ||
| [["no",0.3393537402153015]] |
There was a problem hiding this comment.
| [["no",0.3393537402153015]] | |
| [["no", 0.3393537402153015]] |
|
|
||
| Run the intent catcher: | ||
| ```commandline | ||
| docker compose up --build --abort-on-container-exit --exit-code-from intent_client |
There was a problem hiding this comment.
I suppose this command should be:
docker compose up --build --abort-on-container-exit --exit-code-from intent_catcher for it to run.
Anyways, the command still runs with errors
|
|
||
| Building the bot and launching it in the background can be done with a single command given that the environment variables have been configured correctly. Then you can immediately interact with your bot in Telegram. | ||
| ```commandline | ||
| docker-compose up -d |
There was a problem hiding this comment.
Uniform the commands: with - or without
Description
Examples from demo repository merged into
examples directory.Checklist
Maybe examples should be added to docs?
To tests?
Testing them would require OpenAI and Telegram tokens.
To Consider
.ignorefiles, scripts (such aslint), distribution manifest (if files are added/deleted)