yoelle commited on
Commit
be0f2d3
·
verified ·
1 Parent(s): 9ca6a59

Update Operational_Instructions/AWS_Accounts_for_LiveRAG.md

Browse files
Operational_Instructions/AWS_Accounts_for_LiveRAG.md CHANGED
@@ -51,12 +51,12 @@ For beginners, it is recommended to complete the introductory [AWS tutorials](ht
51
 
52
  # 2. Using the Pre-Built Indices and Building Your Own Indices
53
  We provide you with two basic pre-built dense (Pinecone) and sparse (Opensearch) indices. See usage [here](Indices_Usage_Examples_for_LiveRAG.ipynb). You may use them freely for LiveRAG Challenge tasks only.
54
- You're welcome to build your own Pinecone/OpenSearch, or other indices. We encourage you to take advantage of the AWS and Pinecone credits we provide for this purpose. OpenSearch can be provisioned and paid by AWS credits.\
55
  If you want to build your own Pinecone index follow these [instructions](Pinecone_for_LiveRAG.md).
56
 
57
  # 3. Cost Optimization Recommendations
58
 
59
- We have estimated the cost of a typical team’s infrastructure, including GPU usage, and AWS has provided credits accordingly. However, individual teams may have varying requirements, so cost management is essential:\
60
  - **Shut down unused resources** – Always shut down GPUs and other compute instances when not in use.
61
  - **Experiment on smaller datasets first** – This approach speeds up iteration cycles and reduces expenses before scaling up to larger datasets.
62
 
 
51
 
52
  # 2. Using the Pre-Built Indices and Building Your Own Indices
53
  We provide you with two basic pre-built dense (Pinecone) and sparse (Opensearch) indices. See usage [here](Indices_Usage_Examples_for_LiveRAG.ipynb). You may use them freely for LiveRAG Challenge tasks only.
54
+ You're welcome to build your own Pinecone/OpenSearch, or other indices. We encourage you to take advantage of the AWS and Pinecone credits we provide for this purpose. OpenSearch can be provisioned and paid by AWS credits.
55
  If you want to build your own Pinecone index follow these [instructions](Pinecone_for_LiveRAG.md).
56
 
57
  # 3. Cost Optimization Recommendations
58
 
59
+ We have estimated the cost of a typical team’s infrastructure, including GPU usage, and AWS has provided credits accordingly. However, individual teams may have varying requirements, so cost management is essential:
60
  - **Shut down unused resources** – Always shut down GPUs and other compute instances when not in use.
61
  - **Experiment on smaller datasets first** – This approach speeds up iteration cycles and reduces expenses before scaling up to larger datasets.
62