root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 18:34:36 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

Update Server Instructions (#2113)

Browse Source 
* Update server instructions for web front end
* Update server README
* Remove duplicate OAI instructions
* Fix duplicate text

---------

Co-authored-by: Jesse Johnson <thatguy@jessejojojohnson.com>
This commit is contained in:
Jesse Jojo Johnson 2023-07-05 18:03:19 +00:00 committed by GitHub
parent ec326d350c
commit 983b555e9d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 25 additions and 1 deletions
Show Stats 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
@ -207,3 +207,27 @@ openai.api_base = "http://<Your api-server IP>:port"
```
Then you can utilize llama.cpp as an OpenAI's **chat.completion** or **text_completion** API
### 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>
```