vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update server README

Browse source 
Fix param for setting client path
Add example of front usage
This commit is contained in:
Jesse Johnson 2023-07-05 15:42:26 +00:00
parent 99cf7bcc9a
commit fa4a48cacc
1 changed files with 25 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

26
examples/server/README.md
View file

@ -21,7 +21,7 @@ Command line options:
- `-to N`, `--timeout N`: Server read/write timeout in seconds. Default `600`.
- `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`.
- `--port`: Set the port to listen. Default: `8080`.
- `--public`: path from which to serve static files (default examples/server/public)
- `--path`: path from which to serve static files (default examples/server/public)
- `--embedding`: Enable embedding extraction, Default: disabled.
## Build
@ -191,3 +191,27 @@ Run with bash:
```sh
bash chat.sh
```
### Extending the Web Front End
The default location for the static files is `examples/server/public`. You can extend the front end by running the server binary with `--path` set to `./your-directory` and importing `/completion.js` to get access to the llamaComplete() method. A simple example is below:
```
<html>
<body>
<pre>
<script type="module">
import { llamaComplete } from '/completion.js'
llamaComplete({
prompt: "### Instruction:\nWrite dad jokes, each one paragraph. You can use html formatting if needed.\n\n### Response:",
n_predict: 1024,
},
null,
(chunk) => document.write(chunk.data.content)
)
</script>
</pre>
</body>
</html>
```