cheshire-cat-ai / api-client-py Goto Github PK

🚀 The feature, motivation and pitch

The actually send method (cat_client.py line 120) send a ws message with only "text" parameter. To permit a better integrations with 3rd party tools can be useful to have a second method (eg send_with_params) that permit to send a custom json in additional to text, eg:

"text": message,
"custom_settings": json_string

Obviously this additional setting need to be managed by a plugin on cat server side.

Alternatives

No response

Additional context

No response

Hello Nicola.
Thank you for the answer in the other issue #Furrmidable-Crew/schrodinger_cat#1 (comment).
I tried to upload a .txt from my computer to the cat using https://github.com/cheshire-cat-ai/api-client-py.git and everything worked without any issue.

My goal was to load a document (stored in the plugin folder) inside the declarative memory of the cat just asking it to him.
So I tried to:

1. copy the api-client-py inside the plug-in folder of the cat (with the requirements.txt file) with no modifications.
2. run the plug-in inside the cat

the cat gave me this output error in loading the plugin :

cheshire_cat_core | [2023-09-23 09:43:29.325] WARNING cat.mad_hatter.MadHatter.toggle_plugin::228 => 'Toggle plugin 08_upload file from plug in v3: Activate' cheshire_cat_core | [2023-09-23 09:43:32.106] ERROR cat.mad_hatter.Plugin._load_hooks_and_tools::183 => ('Error in cat.plugins.08_upload file from plug in v3.scripts.release_notes: ' cheshire_cat_core | [2023-09-23 09:43:32.106] ERROR cat.mad_hatter.Plugin._load_hooks_and_tools::183 => "'TAG'")

The question are:

1. is it possible to do what I'm trying to do?
2. It is a error that can be solved easily?
3. is there a more intelligent way to do it with some cat features that I ignore?

This one below is the main code of the plugin but I think it is not required.
tool_caricamento_file.txt

🐛 Describe the bug

`from cheshire_cat_api.api.rabbit_hole_api import RabbitHoleApi
from cheshire_cat_api.api_client import ApiClient
from cheshire_cat_api.configuration import Configuration

file=open("example.txt","w")

conf = Configuration()
api_client=ApiClient(conf)
api_instance = RabbitHoleApi(api_client)
api_response = api_instance.upload_file("example.txt")`

this snippet creates an empty txt file and tries to upload it through the rabbit hole api and fails because the host isn't specified

I believe this is a bug because the rabbit hole api docs say # Defining the host is optional and defaults to http://localhost

Versions

Python 3.10.11
annotated-types==0.6.0
beautifulsoup4==4.12.2
bs4==0.0.1
certifi==2023.11.17
cffi==1.16.0
charset-normalizer==3.3.2
cheshire_cat_api==1.4.1
cryptography==42.0.5
idna==3.6
pdfminer.six==20221105
pdfplumber==0.10.4
Pillow==9.5.0
pycparser==2.21
pycryptodome==3.16.0
pydantic==2.6.2
pydantic_core==2.16.3
PyPDF2==3.0.1
pypdfium2==4.27.0
python-dateutil==2.8.2
requests==2.31.0
six==1.16.0
soupsieve==2.5
typing_extensions==4.9.0
urllib3==2.0.7
websocket-client==1.7.0

🚀 The feature, motivation and pitch

Hi @nicola-corbellini,

I was wondering how I should use this library to interact with the cat from outside: the "send" method looks to be asynchronous but how can I get the result of a message to be used by other services?

Let's say I want to integrate the cat with Microsoft Teams: I'd like to use this library as "man in the middle" but I can't because I can't get the answer from the "send" method.

Am I missing something?

Alternatives

No response

Additional context

No response