fa42757916
* add staging ios app build script * feat(api): add OpenTelemetry LGTM stack for local observability Wire OTel traces, metrics, and logs through a collector to Tempo, Prometheus, and Loki, with custom LLM instrumentation, dev compose overlay, Grafana provisioning, env templates, and development.sh auto-start. Co-authored-by: Cursor <cursoragent@cursor.com> * feat: expand observability, harden dev tooling, and fix expo staging UX Add business and LLM Prometheus metrics with Grafana dashboards, alerting, and a metrics verification script. Wire telemetry through adapters and core LLM paths, and document the local LGTM workflow. Fix development.sh for macOS bash 3.2, open Grafana and eval-web in Chrome, and repair eval-web auto-open (unbound EVAL_WEB_BROWSER_SCHEDULED). Merge internal-eval into the main dev script with improved compose handling. Require EXPO_PUBLIC_* at build time, improve iOS HTTP ATS for staging IPs, show memoir empty state instead of load errors when no chapters exist, and add jest env setup plus chapter list response normalization. Co-authored-by: Cursor <cursoragent@cursor.com> * chore: enable Grafana Assistant Cursor plugin Co-authored-by: Cursor <cursoragent@cursor.com> * fix: memoir empty state and repair withdrawn 0020_chapters_book_id stamp Show empty memoir UI when the chapter list succeeds with no items; treat auth/404 as non-fatal. Extend alembic revision repair so local dev DBs stamped with the removed 0020_chapters_book_id migration can roll back and upgrade to 0019. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Kevin <kevin@brighteng.org> Co-authored-by: Cursor <cursoragent@cursor.com>
82 lines
2.8 KiB
Python
82 lines
2.8 KiB
Python
"""智谱 BigModel 国内 embedding API — 实现 EmbeddingProvider（zai-sdk / ZhipuAiClient）。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
|
||
from zai import ZhipuAiClient
|
||
|
||
from app.core.business_telemetry import business_span
|
||
from app.core.embedding import MEMORY_EMBEDDING_DIMENSION
|
||
from app.core.logging import get_logger
|
||
|
||
_logger = get_logger(__name__)
|
||
|
||
# 单次请求最多 64 条文本（智谱 Embedding-3 文档）
|
||
_EMBED_BATCH_SIZE = 64
|
||
|
||
|
||
class ZhipuEmbeddingProvider:
|
||
def __init__(
|
||
self,
|
||
*,
|
||
api_key: str,
|
||
base_url: str | None = None,
|
||
model: str = "embedding-3",
|
||
) -> None:
|
||
self._model = model
|
||
if not api_key:
|
||
_logger.warning(
|
||
"ZhipuEmbeddingProvider: api_key 为空，embedding 将不可用（记忆检索与 ingest 向量写入会降级）"
|
||
)
|
||
self._client = None
|
||
elif base_url:
|
||
self._client = ZhipuAiClient(
|
||
api_key=api_key,
|
||
base_url=base_url.rstrip("/"),
|
||
)
|
||
else:
|
||
self._client = ZhipuAiClient(api_key=api_key)
|
||
|
||
def is_available(self) -> bool:
|
||
return self._client is not None
|
||
|
||
def _create_vectors_sync(self, texts: list[str]) -> list[list[float]]:
|
||
assert self._client is not None
|
||
resp = self._client.embeddings.create(
|
||
input=texts,
|
||
model=self._model,
|
||
dimensions=MEMORY_EMBEDDING_DIMENSION,
|
||
)
|
||
ordered = sorted(resp.data, key=lambda d: d.index or 0)
|
||
return [list(item.embedding) for item in ordered]
|
||
|
||
async def embed_text(self, text: str) -> list[float]:
|
||
vectors = await self.embed_texts([text])
|
||
return vectors[0] if vectors else []
|
||
|
||
async def embed_texts(self, texts: list[str]) -> list[list[float]]:
|
||
if not self._client or not texts:
|
||
return []
|
||
with business_span("embedding.zhipu.embed", batch_size=len(texts)):
|
||
out: list[list[float]] = []
|
||
for i in range(0, len(texts), _EMBED_BATCH_SIZE):
|
||
batch = texts[i : i + _EMBED_BATCH_SIZE]
|
||
part = await asyncio.to_thread(self._create_vectors_sync, batch)
|
||
out.extend(part)
|
||
return out
|
||
|
||
def embed_text_sync(self, text: str) -> list[float]:
|
||
vecs = self.embed_texts_sync([text])
|
||
return vecs[0] if vecs else []
|
||
|
||
def embed_texts_sync(self, texts: list[str]) -> list[list[float]]:
|
||
if not self._client or not texts:
|
||
return []
|
||
with business_span("embedding.zhipu.embed", batch_size=len(texts)):
|
||
out: list[list[float]] = []
|
||
for i in range(0, len(texts), _EMBED_BATCH_SIZE):
|
||
batch = texts[i : i + _EMBED_BATCH_SIZE]
|
||
out.extend(self._create_vectors_sync(batch))
|
||
return out
|