opencommit 3.2.19 → 3.3.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +23 -2
- package/out/cli.cjs +1664 -1008
- package/package.json +7 -8
package/README.md
CHANGED
|
@@ -90,6 +90,25 @@ export OLLAMA_HOST=0.0.0.0
|
|
|
90
90
|
|
|
91
91
|
This will make Ollama listen on all interfaces, including IPv6 and IPv4, resolving the connection issue. You can add this line to your shell configuration file (like `.bashrc` or `.zshrc`) to make it persistent across sessions.
|
|
92
92
|
|
|
93
|
+
### Running locally with llama.cpp
|
|
94
|
+
|
|
95
|
+
You can run OpenCommit with local models served by [llama.cpp](https://github.com/ggerganov/llama.cpp):
|
|
96
|
+
|
|
97
|
+
- install and build llama.cpp
|
|
98
|
+
- start the server with a GGUF model: `./llama-server -m model.gguf --port 8080`
|
|
99
|
+
- run (in your project directory):
|
|
100
|
+
|
|
101
|
+
```sh
|
|
102
|
+
git add <files...>
|
|
103
|
+
oco config set OCO_AI_PROVIDER='llamacpp' OCO_API_URL='http://localhost:8080'
|
|
104
|
+
```
|
|
105
|
+
|
|
106
|
+
If the server is running on a different machine, set the URL accordingly:
|
|
107
|
+
|
|
108
|
+
```sh
|
|
109
|
+
oco config set OCO_API_URL='http://192.168.1.10:8080'
|
|
110
|
+
```
|
|
111
|
+
|
|
93
112
|
### Flags
|
|
94
113
|
|
|
95
114
|
There are multiple optional flags that can be used with the `oco` command:
|
|
@@ -122,7 +141,7 @@ Create a `.env` file and add OpenCommit config variables there like this:
|
|
|
122
141
|
|
|
123
142
|
```env
|
|
124
143
|
...
|
|
125
|
-
OCO_AI_PROVIDER=<openai (default), anthropic, azure, ollama, gemini, flowise, deepseek, aimlapi>
|
|
144
|
+
OCO_AI_PROVIDER=<openai (default), anthropic, azure, ollama, llamacpp, gemini, flowise, deepseek, aimlapi>
|
|
126
145
|
OCO_API_KEY=<your OpenAI API token> // or other LLM provider API token
|
|
127
146
|
OCO_API_URL=<may be used to set proxy path to OpenAI api>
|
|
128
147
|
OCO_API_CUSTOM_HEADERS=<JSON string of custom HTTP headers to include in API requests>
|
|
@@ -227,7 +246,7 @@ oco models --provider anthropic
|
|
|
227
246
|
|
|
228
247
|
By default OpenCommit uses [OpenAI](https://openai.com).
|
|
229
248
|
|
|
230
|
-
You could switch to [Azure OpenAI Service](https://learn.microsoft.com/azure/cognitive-services/openai/) or Flowise or Ollama.
|
|
249
|
+
You could switch to [Azure OpenAI Service](https://learn.microsoft.com/azure/cognitive-services/openai/) or Flowise or Ollama or llama.cpp.
|
|
231
250
|
|
|
232
251
|
```sh
|
|
233
252
|
oco config set OCO_AI_PROVIDER=azure OCO_API_KEY=<your_azure_api_key> OCO_API_URL=<your_azure_endpoint>
|
|
@@ -235,6 +254,8 @@ oco config set OCO_AI_PROVIDER=azure OCO_API_KEY=<your_azure_api_key> OCO_API_UR
|
|
|
235
254
|
oco config set OCO_AI_PROVIDER=flowise OCO_API_KEY=<your_flowise_api_key> OCO_API_URL=<your_flowise_endpoint>
|
|
236
255
|
|
|
237
256
|
oco config set OCO_AI_PROVIDER=ollama OCO_API_KEY=<your_ollama_api_key> OCO_API_URL=<your_ollama_endpoint>
|
|
257
|
+
|
|
258
|
+
oco config set OCO_AI_PROVIDER=llamacpp OCO_API_URL=<your_llamacpp_endpoint>
|
|
238
259
|
```
|
|
239
260
|
|
|
240
261
|
### Use with Proxy
|