Port docs-mcp-template upgrades (eval, citations, chunking, prefixes) (#16)

Co-authored-by: claude <[email protected]>
This commit was merged in pull request #16.
This commit is contained in:
2026-09-29 22:27:16 -04:00
committed by claude
parent 1a3963f306
commit 92219878d9
13 changed files with 803 additions and 74 deletions
+5 -2
View File
@@ -18,7 +18,7 @@ import chromadb
from chromadb.config import Settings
from .chunk import chunks_from_page
from .embeddings import embedding_function
from .embeddings import EMBED_DOC_PREFIX, embed_texts, embedding_function
log = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
@@ -78,9 +78,12 @@ def upsert_to_chroma(records: list[dict]) -> int:
total = 0
for i in range(0, len(records), BATCH):
chunk = records[i:i + BATCH]
texts = [r["text"] for r in chunk]
vectors = embed_texts(texts, prefix=EMBED_DOC_PREFIX, ef=embedding_function())
col.upsert(
ids=[r["id"] for r in chunk],
documents=[r["text"] for r in chunk],
documents=texts,
embeddings=vectors,
metadatas=[r["metadata"] for r in chunk],
)
total += len(chunk)