HomerandClaude Opus 5.5
f9bad01ed7
ci / check (push) Waiting to run
The first public release of LLeMbas CLI: a terminal coding agent and project manager for any LLM API, with permission modes, git snapshots, memory and skills, knowledge bases, MCP, voice, and a link to a LLeMbas instance whose web UI can work its sessions too. Signed Linux binaries for x64 and arm64. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
61 lines
2.9 KiB
TypeScript
61 lines
2.9 KiB
TypeScript
// Embeddings for the library: `embedding: connection/model` in config.yaml, over the connection's
|
|
// OpenAI-shaped /embeddings (llama.cpp with --embedding, vLLM, LM Studio, OpenAI…) or Ollama's
|
|
// /api/embed. Vectors are made unit length here, so a dot product is the cosine.
|
|
import { resolveKey, type Loaded } from "../config/load.ts"
|
|
import { authHeaders, joinUrl, request, tlsFor } from "../provider/http.ts"
|
|
import { resolveModel } from "../provider/index.ts"
|
|
import type { Embedder } from "./store.ts"
|
|
|
|
function unit(v: number[]): Float32Array {
|
|
let n = 0
|
|
for (const x of v) n += x * x
|
|
n = Math.sqrt(n) || 1
|
|
return Float32Array.from(v, (x) => x / n)
|
|
}
|
|
|
|
export function embedderFor(loaded: Loaded, ref: string | undefined): Embedder | undefined {
|
|
if (!ref) return undefined
|
|
// Through the same resolver as every model ref: an instance's model by its provider
|
|
// (`llama/nomic-embed`) or in the older form (`example/nomic-embed`). The name stored with the
|
|
// vectors stays the ref as written, so a library indexed under it is still found.
|
|
// An embedding model need not be listed on its connection (`connection/<any id>`, as before).
|
|
let name: string
|
|
let id: string
|
|
try {
|
|
const resolved = resolveModel(loaded, ref)
|
|
name = resolved.connectionName
|
|
id = resolved.id
|
|
} catch (e) {
|
|
// An instance's embedding model by its served id (`llama/nomic-embed`): not a
|
|
// model ref, since only chat models are (lembas/webui.ts, isChatModel), so found by the ids
|
|
// its connection says it serves.
|
|
const served = Object.entries(loaded.connections).find(([, c]) => (c as { webui?: { embeddings?: string[] } }).webui?.embeddings?.includes(ref))
|
|
const slash = ref.indexOf("/")
|
|
if (served) {
|
|
name = served[0]
|
|
id = ref
|
|
} else {
|
|
if (slash <= 0) throw new Error(`embedding: "${ref}" must be written connection/model`)
|
|
name = ref.slice(0, slash)
|
|
id = ref.slice(slash + 1)
|
|
if (!loaded.connections[name]) throw new Error(`embedding: ${(e as Error).message}`)
|
|
}
|
|
}
|
|
const c = loaded.connections[name]!
|
|
if (c.dialect === "anthropic" || c.dialect === "gemini") throw new Error(`embedding: the ${c.dialect} dialect has no embeddings here; use an OpenAI-compatible or Ollama connection`)
|
|
const ollama = c.dialect === "ollama"
|
|
return {
|
|
model: ref,
|
|
async embed(texts, signal) {
|
|
const res = await request(
|
|
joinUrl(c.base_url, ollama ? "api/embed" : "embeddings"),
|
|
{ method: "POST", headers: authHeaders(c, resolveKey(name, c)), body: JSON.stringify({ model: id, input: texts }), signal, timeoutMs: (c.timeout ?? 120) * 1000, tls: tlsFor(c) },
|
|
`${ref} (embeddings)`,
|
|
)
|
|
const j = (await res.json()) as { data?: { embedding: number[]; index?: number }[]; embeddings?: number[][] }
|
|
const rows = ollama ? (j.embeddings ?? []) : [...(j.data ?? [])].sort((a, b) => (a.index ?? 0) - (b.index ?? 0)).map((d) => d.embedding)
|
|
return rows.map(unit)
|
|
},
|
|
}
|
|
}
|