happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SimpleChatTC:Cleanup:ChatProps: iRecentUserMsgCnt 

Update Me class

Update show settings

Update show props info

Update readme
This commit is contained in:
hanishkvc 2025-10-21 23:44:39 +05:30
parent 7409b29862
commit 78ccca056f
2 changed files with 30 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
tools/server/public_simplechat/readme.md
View File

@ -191,6 +191,17 @@ It is attached to the document object. Some of these can also be updated using t
inturn the machine goes into power saving mode or so, the platform may stop network connection,
leading to exception.
iRecentUserMsgCnt - a simple minded SlidingWindow to limit context window load at Ai Model end.
This is set to 10 by default. So in addition to latest system message, last/latest iRecentUserMsgCnt
user messages after the latest system prompt and its responses from the ai model will be sent
to the ai-model, when querying for a new response. Note that if enabled, only user messages after
the latest system message/prompt will be considered.
This specified sliding window user message count also includes the latest user query.
<0 : Send entire chat history to server
0 : Send only the system message if any to the server
>0 : Send the latest chat history from the latest system prompt, limited to specified cnt.
tools - contains controls related to tool calling
enabled - control whether tool calling is enabled or not
@ -250,22 +261,12 @@ It is attached to the document object. Some of these can also be updated using t
Content-Type is set to application/json. Additionally Authorization entry is provided, which can
be set if needed using the settings ui.
iRecentUserMsgCnt - a simple minded SlidingWindow to limit context window load at Ai Model end.
This is set to 10 by default. So in addition to latest system message, last/latest iRecentUserMsgCnt
user messages after the latest system prompt and its responses from the ai model will be sent
to the ai-model, when querying for a new response. Note that if enabled, only user messages after
the latest system message/prompt will be considered.
This specified sliding window user message count also includes the latest user query.
<0 : Send entire chat history to server
0 : Send only the system message if any to the server
>0 : Send the latest chat history from the latest system prompt, limited to specified cnt.
By using gMe's iRecentUserMsgCnt and apiRequestOptions.max_tokens/n_predict one can try to control
the implications of loading of the ai-model's context window by chat history, wrt chat response to
some extent in a simple crude way. You may also want to control the context size enabled when the
server loads ai-model, on the server end.
By using gMe's chatProps.iRecentUserMsgCnt and apiRequestOptions.max_tokens/n_predict one can try to
control the implications of loading of the ai-model's context window by chat history, wrt chat response
to some extent in a simple crude way. You may also want to control the context size enabled when the
server loads ai-model, on the server end. One can look at the current context size set on the server
end by looking at the settings/info block shown when ever one switches-to/is-shown a new session.
Sometimes the browser may be stuborn with caching of the file, so your updates to html/css/js
@ -288,8 +289,8 @@ the system prompt, anytime during the conversation or only at the beginning.
By default things are setup to try and make the user experience a bit better, if possible.
However a developer when testing the server of ai-model may want to change these value.
Using iRecentUserMsgCnt reduce chat history context sent to the server/ai-model to be
just the system-prompt, prev-user-request-and-ai-response and cur-user-request, instead of
Using chatProps.iRecentUserMsgCnt reduce chat history context sent to the server/ai-model to be
just the system-prompt, few prev-user-requests-and-ai-responses and cur-user-request, instead of
full chat history. This way if there is any response with garbage/repeatation, it doesnt
mess with things beyond the next question/request/query, in some ways. The trim garbage
option also tries to help avoid issues with garbage in the context to an extent.

24
tools/server/public_simplechat/simplechat.js
View File

@ -413,7 +413,7 @@ class SimpleChat {
div.replaceChildren();
}
let last = undefined;
for(const x of this.recent_chat(gMe.iRecentUserMsgCnt)) {
for(const x of this.recent_chat(gMe.chatProps.iRecentUserMsgCnt)) {
let entry = ui.el_create_append_p(`${x.ns.role}: ${x.content_equiv()}`, div);
entry.className = `role-${x.ns.role}`;
last = entry;
@ -473,7 +473,7 @@ class SimpleChat {
*/
request_messages_jsonstr() {
let req = {
messages: this.recent_chat_ns(gMe.iRecentUserMsgCnt),
messages: this.recent_chat_ns(gMe.chatProps.iRecentUserMsgCnt),
}
return this.request_jsonstr_extend(req);
}
@ -485,7 +485,7 @@ class SimpleChat {
request_prompt_jsonstr(bInsertStandardRolePrefix) {
let prompt = "";
let iCnt = 0;
for(const msg of this.recent_chat(gMe.iRecentUserMsgCnt)) {
for(const msg of this.recent_chat(gMe.chatProps.iRecentUserMsgCnt)) {
iCnt += 1;
if (iCnt > 1) {
prompt += "\n";
@ -1021,11 +1021,11 @@ class Me {
};
this.chatProps = {
stream: true,
}
iRecentUserMsgCnt: 10,
};
this.bCompletionFreshChatAlways = true;
this.bCompletionInsertStandardRolePrefix = false;
this.bTrimGarbage = true;
this.iRecentUserMsgCnt = 10;
/** @type {Object<string, number>} */
this.sRecentUserMsgCnt = {
"Full": -1,
@ -1094,9 +1094,9 @@ class Me {
* @param {boolean} bAll
*/
show_info(elDiv, bAll=false) {
let props = ["baseURL", "modelInfo","headers", "tools", "apiRequestOptions", "apiEP", "chatProps", "iRecentUserMsgCnt", "bTrimGarbage", "bCompletionFreshChatAlways", "bCompletionInsertStandardRolePrefix"];
let props = ["baseURL", "modelInfo","headers", "tools", "apiRequestOptions", "apiEP", "chatProps", "bTrimGarbage", "bCompletionFreshChatAlways", "bCompletionInsertStandardRolePrefix"];
if (!bAll) {
props = [ "baseURL", "modelInfo", "headers", "tools", "apiRequestOptions", "apiEP", "chatProps", "iRecentUserMsgCnt" ];
props = [ "baseURL", "modelInfo", "headers", "tools", "apiRequestOptions", "apiEP", "chatProps" ];
}
fetch(`${this.baseURL}/props`).then(resp=>resp.json()).then(json=>{
this.modelInfo = {
@ -1112,12 +1112,12 @@ class Me {
* @param {HTMLDivElement} elDiv
*/
show_settings(elDiv) {
ui.ui_show_obj_props_edit(elDiv, "", this, ["baseURL", "headers", "tools", "apiRequestOptions", "apiEP", "chatProps", "iRecentUserMsgCnt", "bTrimGarbage", "bCompletionFreshChatAlways", "bCompletionInsertStandardRolePrefix"], "Settings", (prop, elProp)=>{
ui.ui_show_obj_props_edit(elDiv, "", this, ["baseURL", "headers", "tools", "apiRequestOptions", "apiEP", "chatProps", "bTrimGarbage", "bCompletionFreshChatAlways", "bCompletionInsertStandardRolePrefix"], "Settings", (prop, elProp)=>{
if (prop == "headers:Authorization") {
// @ts-ignore
elProp.placeholder = "Bearer OPENAI_API_KEY";
}
}, [":apiEP", ":iRecentUserMsgCnt"], (propWithPath, prop, elParent)=>{
}, [":apiEP", ":chatProps:iRecentUserMsgCnt"], (propWithPath, prop, elParent)=>{
if (propWithPath == ":apiEP") {
let sel = ui.el_creatediv_select("SetApiEP", "ApiEndPoint", ApiEP.Type, this.apiEP, (val)=>{
// @ts-ignore
@ -1125,9 +1125,9 @@ class Me {
});
elParent.appendChild(sel.div);
}
if (propWithPath == ":iRecentUserMsgCnt") {
let sel = ui.el_creatediv_select("SetChatHistoryInCtxt", "ChatHistoryInCtxt", this.sRecentUserMsgCnt, this.iRecentUserMsgCnt, (val)=>{
this.iRecentUserMsgCnt = this.sRecentUserMsgCnt[val];
if (propWithPath == ":chatProps:iRecentUserMsgCnt") {
let sel = ui.el_creatediv_select("SetChatHistoryInCtxt", "ChatHistoryInCtxt", this.sRecentUserMsgCnt, this.chatProps.iRecentUserMsgCnt, (val)=>{
this.chatProps.iRecentUserMsgCnt = this.sRecentUserMsgCnt[val];
});
elParent.appendChild(sel.div);
}