Skip to content

fix: use configured models instead of hardcoded defaults #564

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jowitte wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: use configured models instead of hardcoded defaults #564

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 10 additions & 8 deletions src/cli/qmd.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ import {
type ReindexResult,
type ChunkStrategy,
} from "../store.js";
import { disposeDefaultLlamaCpp, getDefaultLlamaCpp, setDefaultLlamaCpp, LlamaCpp, withLLMSession, pullModels, DEFAULT_EMBED_MODEL_URI, DEFAULT_GENERATE_MODEL_URI, DEFAULT_RERANK_MODEL_URI, DEFAULT_MODEL_CACHE_DIR } from "../llm.js";
import { disposeDefaultLlamaCpp, getDefaultLlamaCpp, setDefaultLlamaCpp, LlamaCpp, withLLMSession, pullModels, DEFAULT_EMBED_MODEL_URI, DEFAULT_MODEL_CACHE_DIR } from "../llm.js";
import {
formatSearchResults,
formatDocuments,
Expand Down Expand Up @@ -462,9 +462,10 @@ async function showStatus(): Promise<void> {
return match ? `https://huggingface.co/${match[1]}` : uri;
};
console.log(`\n${c.bold}Models${c.reset}`);
console.log(` Embedding: ${hfLink(DEFAULT_EMBED_MODEL_URI)}`);
console.log(` Reranking: ${hfLink(DEFAULT_RERANK_MODEL_URI)}`);
console.log(` Generation: ${hfLink(DEFAULT_GENERATE_MODEL_URI)}`);
const llm = getDefaultLlamaCpp();
console.log(` Embedding: ${hfLink(llm.embedModelName)}`);
console.log(` Reranking: ${hfLink(llm.rerankModelName)}`);
console.log(` Generation: ${hfLink(llm.generateModelName)}`);
}

// Device / GPU info
Expand Down Expand Up @@ -3107,7 +3108,7 @@ if (isMain) {
const maxDocsPerBatch = parseEmbedBatchOption("maxDocsPerBatch", cli.values["max-docs-per-batch"]);
const maxBatchMb = parseEmbedBatchOption("maxBatchBytes", cli.values["max-batch-mb"]);
const embedChunkStrategy = parseChunkStrategy(cli.values["chunk-strategy"]);
await vectorIndex(DEFAULT_EMBED_MODEL_URI, !!cli.values.force, {
await vectorIndex(getDefaultLlamaCpp().embedModelName, !!cli.values.force, {
maxDocsPerBatch,
maxBatchBytes: maxBatchMb === undefined ? undefined : maxBatchMb * 1024 * 1024,
chunkStrategy: embedChunkStrategy,
Expand All @@ -3120,10 +3121,11 @@ if (isMain) {

case "pull": {
const refresh = cli.values.refresh === undefined ? false : Boolean(cli.values.refresh);
const llm = getDefaultLlamaCpp();
const models = [
DEFAULT_EMBED_MODEL_URI,
DEFAULT_GENERATE_MODEL_URI,
DEFAULT_RERANK_MODEL_URI,
llm.embedModelName,
llm.generateModelName,
llm.rerankModelName,
];
console.log(`${c.bold}Pulling models${c.reset}`);
const results = await pullModels(models, {
Expand Down
8 changes: 8 additions & 0 deletions src/llm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -514,6 +514,14 @@ export class LlamaCpp implements LLM {
return this.embedModelUri;
}

get generateModelName(): string {
return this.generateModelUri;
}

get rerankModelName(): string {
return this.rerankModelUri;
}

/**
* Reset the inactivity timer. Called after each model operation.
* When timer fires, models are unloaded to free memory (if no active sessions).
Expand Down