github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 04:07:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

mistral: comment batching param (#20868)

Browse Source 
Addresses #20523
This commit is contained in:
Erick Friis 2024-04-24 17:38:21 -07:00 committed by GitHub
parent 7c5063ef60
commit 5da9dd1195
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libs/partners/mistralai/langchain_mistralai/embeddings.py
View File

@ -18,6 +18,10 @@ from tokenizers import Tokenizer # type: ignore
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
MAX_TOKENS = 16_000 MAX_TOKENS = 16_000
"""A batching parameter for the Mistral API. This is NOT the maximum number of tokens
accepted by the embedding model for each document/chunk, but rather the maximum number
of tokens that can be sent in a single request to the Mistral API (across multiple
documents/chunks)"""
class DummyTokenizer: class DummyTokenizer: