Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/blwsh/llmt
Transforms all files in specified directory using a large language model like ChatGPT
https://github.com/blwsh/llmt
automation chatgpt golang llama3 ollama transformer translate
Last synced: 3 months ago
JSON representation
Transforms all files in specified directory using a large language model like ChatGPT
- Host: GitHub
- URL: https://github.com/blwsh/llmt
- Owner: blwsh
- License: unlicense
- Created: 2024-07-20T08:34:25.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-09-16T14:58:06.000Z (5 months ago)
- Last Synced: 2024-09-17T09:18:51.136Z (4 months ago)
- Topics: automation, chatgpt, golang, llama3, ollama, transformer, translate
- Language: Go
- Homepage:
- Size: 82 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LLMT - Large Language Model Transformer
Transforms all files in specified directory using a large language model. You can specify conditions for file
transformation along with a prompt, which LLM to use and which model should be used . The transformed files are saved in
a new directory. The file structure is preserved.
## Usage
### Command line usage
#### Docker
```shell
docker run -v $(pwd):/data ghcr.io/blwsh/llmt analyze
```
> [!NOTE]
> When using `openai` analyzer you'll need to provide an API key. You can do this by setting the `OPENAI_TOKEN`
> environment variable.
#### Release
Download the latest release from the [releases page](https://github.com/blwsh/llmt/releases). Extract the archive and
run the binary.
```shell
llmt \ --config \ # optional parameter, default is config.yaml in current directory
analyze ./myProject ../docs # analyzes files in ./myProject and outputs them as markdown in ../docs (maintains file structure)
```
### Configuration
Example `config.yaml` file:
```yaml
#$schema: https://raw.githubusercontent.com/blwsh/llmt/main/schema.json
version: "0.1"
analyzers:
- prompt: Write docs for this file
analyzer: openai
model: gpt-4o-mini
regex: ^.+\.php$
not_in:
- vendor
```
#### Analyzer configuration
| Field | Description | Required | Default |
|----------|-------------------------------------------------------------------------------------------------------------|----------|---------|
| prompt | The prompt to use for the language model | yes | |
| analyzer | Specifies which llm to use. See [Available analyzers](#available-analyzers) for the full list of analyzers. | yes | |
| model | The model to use for the language model. If you use a fine tuned openai model, you set its name here. | yes | |
| regex | A regex to match the file path. | no | |
| not_in | A list of directories to exclude from the analysis. | no | |
| in | A list of directories to include in the analysis. Note: not_in takes precedence over `in`. | no | |
See [schema.json](schema.json) for the full config schema.
##### Available analyzers
| Analyzer | Description |
|----------|--------------------------------------------------------------------------------------------------------------------------------|
| openai | Uses the OpenAI API to transform the files. You need to provide an API key via the `OPENAI_TOKEN` environment variable. |
| ollama | Uses the OLLAMA API to transform the files. You can override the ollama url by setting the `OLLAMA_HOST` environment variable. |
## Go usage
You can find a comprehensive list of [examples](examples) here. Below is a simple example which has similar behaviour to
the command line analyze command.
Click to expand!
```go
package main
import (
"context"
"io/ioutil"
"strings"
"github.com/blwsh/llmt/pkg/analyzer"
"github.com/blwsh/llmt/pkg/analyzer/item_analyzer/openai"
"github.com/blwsh/llmt/pkg/analyzer/project_analyzer/chat"
)
func main() {
chat.New().
AnalyzeProject(context.Background(), "./myProject", "../docs", []analyzer.FileAnalyzerConfig{
{
Prompt: "document this files behaviour",
Analyzer: openai.New("OPENAI_TOKEN_HERE", "gpt-4o-mini"),
Condition: func(path string) bool { return strings.HasSuffix(path, ".php") },
ResultHandler: func(destFilepath string, result string) error {
return ioutil.WriteFile(destFilepath, []byte(result), 0644)
},
},
})
}
```
With `Condition` and `ResultHandler` you're able to filter out which files should be processed and how the result should
be processed.
> [!TIP]
> To see a more complete example of the above snippet, see [examples/overview](examples/overview/main.go) directory.
## Development
All contributions welcome! For the next release I want to offer more analyzers with greater configurability. I also plan
on adding more hooks for file analyzers to allow for more complex transformations.