phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-06 04:34:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add a special header per-client call to parser provider data

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-18 09:17:59 -07:00 • committed by Xi Yan
parent a6be32bc3d
commit 32beecb20d
11 changed files with 955 additions and 104 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/utils/memory/vector_store.py
View file

@ -16,6 +16,7 @@ import httpx
import numpy as np
from numpy.typing import NDArray
from pypdf import PdfReader
from termcolor import cprint
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_models.llama3.api.tokenizer import Tokenizer
@ -160,6 +161,8 @@ class BankWithIndex:
self.bank.config.overlap_size_in_tokens
or (self.bank.config.chunk_size_in_tokens // 4),
)
if not chunks:
continue
embeddings = model.encode([x.content for x in chunks]).astype(np.float32)
await self.index.add_chunks(chunks, embeddings)