Cloudflare Workers AI
Cloudflare, Inc. (Wikipedia) is an American company that provides content delivery network services, cloud cybersecurity, DDoS mitigation, and ICANN-accredited domain registration services.
Cloudflare Workers AI allows you to run machine learning models, on the
Cloudflarenetwork, from your code via REST API.
Workers AI Developer Docs lists all text embeddings models available.
Setting up
Both a Cloudflare Account ID and Workers AI API token are required. Find how to obtain them fromthis document.
You can pass these parameters explicitly or define as environmental variables.
import os
from dotenvimport load_dotenv
load_dotenv(".env")
cf_acct_id= os.getenv("CF_ACCOUNT_ID")
cf_ai_token= os.getenv("CF_AI_API_TOKEN")
Example
from langchain_cloudflare.embeddingsimport(
CloudflareWorkersAIEmbeddings,
)
embeddings= CloudflareWorkersAIEmbeddings(
account_id=cf_acct_id,
api_token=cf_ai_token,
model_name="@cf/baai/bge-small-en-v1.5",
)
# single string embeddings
query_result= embeddings.embed_query("test")
len(query_result), query_result[:3]
(384, [-0.033660888671875, 0.039764404296875, 0.03558349609375])
# string embeddings in batches
batch_query_result= embeddings.embed_documents(["test1","test2","test3"])
len(batch_query_result),len(batch_query_result[0])
(3, 384)
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides