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

SimpleChat: model request field for openai/equivalent compat

Browse source 
May help testing with openai/equivalent web services, if they
require this field.
This commit is contained in:
HanishKVC 2024-05-29 23:23:50 +05:30
parent 85fd2d0d84
commit 0e7880a694
2 changed files with 8 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/public_simplechat/readme.md
View file

@ -30,7 +30,7 @@ NOTE: Wrt options sent with the request, it mainly sets temperature, max_tokens
However if someone wants they can update the js file or equivalent member in gMe as needed. However if someone wants they can update the js file or equivalent member in gMe as needed.
NOTE: One may be able to use this to chat with openai api web-service /chat/completions endpoint, in a very NOTE: One may be able to use this to chat with openai api web-service /chat/completions endpoint, in a very
limited / minimal way. One will need to set openai url and authorization bearer key in settings ui. limited / minimal way. One will need to set model, openai url and authorization bearer key in settings ui.
## usage ## usage
@ -232,7 +232,7 @@ for a minimal chatting experimentation by setting the below.
* https://api.openai.com/v1 or similar * https://api.openai.com/v1 or similar
* Wrt request body - gMe.chatRequestOptions * Wrt request body - gMe.chatRequestOptions
* model * model (settings ui)
* any additional fields if required in future * any additional fields if required in future
* Wrt request headers - gMe.headers * Wrt request headers - gMe.headers

6
examples/server/public_simplechat/simplechat.js
View file

@ -699,6 +699,7 @@ class Me {
} }
// Add needed fields wrt json object to be sent wrt LLM web services completions endpoint. // Add needed fields wrt json object to be sent wrt LLM web services completions endpoint.
this.chatRequestOptions = { this.chatRequestOptions = {
"model": "gpt-3.5-turbo",
"temperature": 0.7, "temperature": 0.7,
"max_tokens": 1024, "max_tokens": 1024,
"n_predict": 1024, "n_predict": 1024,
@ -763,6 +764,11 @@ class Me {
inp.el.placeholder = "Bearer OPENAI_API_KEY"; inp.el.placeholder = "Bearer OPENAI_API_KEY";
elDiv.appendChild(inp.div); elDiv.appendChild(inp.div);
inp = ui.el_creatediv_input("SetModel", "Model", "text", this.chatRequestOptions["model"], (val)=>{
this.chatRequestOptions["model"] = val;
});
elDiv.appendChild(inp.div);
let bb = ui.el_creatediv_boolbutton("SetStream", "Stream", {true: "[+] yes stream", false: "[-] do oneshot"}, this.bStream, (val)=>{ let bb = ui.el_creatediv_boolbutton("SetStream", "Stream", {true: "[+] yes stream", false: "[-] do oneshot"}, this.bStream, (val)=>{
this.bStream = val; this.bStream = val;
}); });