No-code AI chatbot using Ollama.
Project description
LlamaScript
LlamaScript is a no-code AI chatbot using Ollama.
Table of Contents
Installation
You can install LlamaScript using pip:
pip install llamascript
Usage
To use LlamaScript, create a llama file (no file extension) with the following commands:
IGNORE: Use this before the CHAT command to supress the welcome message.
USE <model>: This command loads the specified model.
SYSTEM <message>: This command sets the system prompt.
PROMPT <message>: This command sets the message to be sent to the chatbot.
CHAT: This command sends the message to the chatbot and prints the response.
Here's an example:
IGNORE
USE llama3
PROMPT Hello, how are you?
CHAT
Note: For more examples see here.
You can then run LlamaScript with the following command:
llamascript
LlamaScript usually has a file extension of .llama
, but if it is ran as a main script, it is usually llama
(no file extension).
License
LlamaScript is licensed under the Apache 2.0 License.
Roadmap
Things to come in the future:
- An
API
command to serve on Flask
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
llamascript-0.5.0.tar.gz
(8.6 kB
view details)
Built Distribution
File details
Details for the file llamascript-0.5.0.tar.gz
.
File metadata
- Download URL: llamascript-0.5.0.tar.gz
- Upload date:
- Size: 8.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.9.19
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 313b5c84cf23825fad32ce130755f64b86701d253c255d4a171dc68348ab46b4 |
|
MD5 | 8e06b869f0bba3988c4e83dbc98f6d1b |
|
BLAKE2b-256 | 7f30288c1a3ac56f29b74b7bd1dfbf43f9dba90c29de0c57c62a5996d1c2cadb |
Provenance
File details
Details for the file llamascript-0.5.0-py3-none-any.whl
.
File metadata
- Download URL: llamascript-0.5.0-py3-none-any.whl
- Upload date:
- Size: 9.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.9.19
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 35d1ac37ca83713bb9c9606e4e2f0fec00c436ea3e9c16999b8e7ffb34ae18e2 |
|
MD5 | fbbdfe3ca007ac37c9c247e671957477 |
|
BLAKE2b-256 | 031798a41ec0c3d89ecb217ffe77882ca6cd6c77df26a26b99b53863873832c1 |