https://github.com/emi420/ollama-batch
This simple utility will runs LLM prompts over a list of texts or images for classify them, printing the results as a JSON response.
https://github.com/emi420/ollama-batch
ai data-science llm ollama
Last synced: 10 months ago
JSON representation
This simple utility will runs LLM prompts over a list of texts or images for classify them, printing the results as a JSON response.
- Host: GitHub
- URL: https://github.com/emi420/ollama-batch
- Owner: emi420
- License: agpl-3.0
- Created: 2024-05-23T21:46:37.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2025-08-15T14:42:57.000Z (11 months ago)
- Last Synced: 2025-08-15T15:40:09.918Z (11 months ago)
- Topics: ai, data-science, llm, ollama
- Language: Python
- Homepage:
- Size: 829 KB
- Stars: 9
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Ollama Batch Classification Tool
This simple utility will runs LLM prompts over a list of texts
or images for classify them, printing the results as a JSON response.
## Quick start
### Requirements
You'll need Ollama installed in your system.
Default model is `gemma3:4b`, but you can use any other model with the `-m ` parameter.
### Install
```bash
pip install ollama-batch
```
### Usage
```bash
ollama-batch -f -f examples/recipes.json -p 'Is this recipe a sweet dessert or salty food?'
```
```json
[
{"result": "salty"},
{"result": "sweet"},
{"result": "salty"},
{"result": "sweet"},
{"result": "sweet"},
{"result": "sweet"}
]
```
### Other examples
```bash
ollama-batch -d examples/recipes -p 'Is this recipe a sweet dessert or salty food?' --json-property=ingredients
ollama-batch -d examples/recipes -p 'Is this recipe a sweet dessert or salty food?' --json-property=title
ollama-batch -f examples/recipes.json --prompt-file examples/sweet_or_salty.txt
ollama-batch -f examples/recipes.json --prompt-file examples/sweet_or_salty.txt --json-append=title,url
ollama-batch -d examples/images -i --prompt-file examples/sweet_or_salty.txt
```
### Help
```bash
ollama-batch \
[--directory DIRECTORY] \
[--file FILE] [--model MODEL] \
[--prompt PROMPT] \
[--prompt-file PROMPT_FILE] \
[--json-property JSON_PROPERTY] \
[--json-append JSON_APPEND] \
[--question-first]
options:
-h, --help
Show this help message and exit
--directory DIRECTORY, -d DIRECTORY
Directory with files you want to process
--file FILE, -f FILE
JSON file you want to process
--model MODEL, -m MODEL
Model you want to use
--prompt PROMPT, -p PROMPT
Prompt text
--prompt-file PROMPT_FILE
Text file with a prompt
--json-property JSON_PROPERTY
JSON property that you want to use
--json-append JSON_APPEND
Property that you want to append to the results
--question-first
First the question, then the prompt
--images, -i
Look for images (use a vision model)
```
### License
You may use this project under the terms of the GNU Affero General Public License (GNU AGPL) Version 3.
(c) 2024 Emilio Mariscal