Spaces:
Sleeping
Sleeping
Update LiveRAG_README.md
Browse files- LiveRAG_README.md +10 -10
LiveRAG_README.md
CHANGED
@@ -4,36 +4,36 @@
|
|
4 |
|
5 |
|
6 |
|
7 |
-
# 1.
|
8 |
|
9 |
|
10 |
|
11 |
## 1.1 Setting up your AWS accounts - See [AWS Accounts instructions - section 1](Operational_Instructions/AWS_Accounts_for_LiveRAG.md) for the full details
|
12 |
|
13 |
-
1. Accessing the AWS LiveRAG account - follow the instructions you received by email
|
14 |
-
2. Applying your AWS credits to your team account - follow the instructions you received by email
|
15 |
**CAVEAT: The credits are valid for the use of AWS services only and you will be responsible for any Bedrock 3rd Party FM billing as well as any solution from our partners listed in AWS Marketplace, such as Pinecone. IF YOU EXCEED YOUR CREDITS, YOU WILL BE DIRECTED CHARGED AND NOT BE REFUNDED BY THE ORGANIZERS**
|
16 |
|
17 |
|
18 |
## 1.2 Setting your Pinecone account if you want to build your own dense index
|
19 |
|
20 |
-
1. Sign up for a [Pinecone](https://pinecone.io ) account, adding a payment method (upgrade to standard). You will not be charged at this time
|
21 |
-
2. Send mail sigir2025-liverag-tech@tii.ae with your team information and Pinecone account name and we will apply the $750 credits to your account
|
22 |
**Remark:** Do you use Pinecone servcies until you see the allocated credits appear in your account, otherwise you will be charged
|
23 |
|
24 |
## 1.3. Register to AI71-Platform to access DataMorgana and Falcon3-10B-Instruct LLM
|
25 |
|
26 |
-
1. Register to [AI71-Platform](https://platform.ai71.ai/register) and send the email address used for registration to sigir2025-liverag-tech@tii.ae
|
27 |
2. After you're notified that you are approved, login to your [AI71-Platform account](https://platform.ai71.ai)
|
28 |
|
29 |
|
30 |
---
|
31 |
-
# 2.
|
32 |
|
33 |
## 2.1 Accessing or building your RAG indices
|
34 |
You can use the pre-built indices, [Pinecone](https://www.pinecone.io/) and [OpenSearch](https://opensearch.org/) or build your own indices on top of the same of [FineWeb Sample-10BT](https://huggingface.co/datasets/HuggingFaceFW/fineweb/viewer/sample-10BT) corpus
|
35 |
1. To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)
|
36 |
-
2. To build your own **OpenSearch** index, create or use your existing AWS account and apply the provided AWS credits to save costs (see [here](Operational_Instructions/AWS_Accounts_for_LiveRAG.md))
|
37 |
3. To build your own **Pinecone** index, create or use your existing Pinecone account and apply the provided Pinecone credits to save costs (see [here](Operational_Instructions/Pinecone_for_LiveRAG.md))
|
38 |
|
39 |
## 2.2 Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform
|
@@ -44,12 +44,12 @@
|
|
44 |
3.2 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))
|
45 |
**Remark:** Accessing Falcon via the AI71-Platform API is optional and recommended for a quick start. However, for a robust solution, suitable for the live event, it is recommended to set up your own Falcon3-10B-Instruct instance
|
46 |
|
47 |
-
## 2.3. Building, training, and evaluating your RAG system
|
48 |
1. Build your RAG system in your AWS Team account leveraging your FineWeb indices - make sure to use Falcon3-10B-Instruct to generate answers
|
49 |
2. Train your RAG system using synthetic Q&A pairs generated by DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb)
|
50 |
3. Evaluate your RAG system using the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md)
|
51 |
|
52 |
-
## 4. LiveRAG
|
53 |
|
54 |
You may contact the organizers via:
|
55 |
- sigir2025-liverag-gen@tii.ae - for general issues
|
|
|
4 |
|
5 |
|
6 |
|
7 |
+
# 1. LiveRAG Challenge Onboarding
|
8 |
|
9 |
|
10 |
|
11 |
## 1.1 Setting up your AWS accounts - See [AWS Accounts instructions - section 1](Operational_Instructions/AWS_Accounts_for_LiveRAG.md) for the full details
|
12 |
|
13 |
+
1. Accessing the AWS LiveRAG account - follow the instructions you received by email
|
14 |
+
2. Applying your AWS credits to your team account - follow the instructions you received by email
|
15 |
**CAVEAT: The credits are valid for the use of AWS services only and you will be responsible for any Bedrock 3rd Party FM billing as well as any solution from our partners listed in AWS Marketplace, such as Pinecone. IF YOU EXCEED YOUR CREDITS, YOU WILL BE DIRECTED CHARGED AND NOT BE REFUNDED BY THE ORGANIZERS**
|
16 |
|
17 |
|
18 |
## 1.2 Setting your Pinecone account if you want to build your own dense index
|
19 |
|
20 |
+
1. Sign up for a [Pinecone](https://pinecone.io ) account, adding a payment method (upgrade to standard). You will not be charged at this time
|
21 |
+
2. Send mail sigir2025-liverag-tech@tii.ae with your team information and Pinecone account name and we will apply the $750 credits to your account
|
22 |
**Remark:** Do you use Pinecone servcies until you see the allocated credits appear in your account, otherwise you will be charged
|
23 |
|
24 |
## 1.3. Register to AI71-Platform to access DataMorgana and Falcon3-10B-Instruct LLM
|
25 |
|
26 |
+
1. Register to [AI71-Platform](https://platform.ai71.ai/register) and send the email address used for registration to sigir2025-liverag-tech@tii.ae
|
27 |
2. After you're notified that you are approved, login to your [AI71-Platform account](https://platform.ai71.ai)
|
28 |
|
29 |
|
30 |
---
|
31 |
+
# 2. LiveRAG Challenge Step-by-Step Guide
|
32 |
|
33 |
## 2.1 Accessing or building your RAG indices
|
34 |
You can use the pre-built indices, [Pinecone](https://www.pinecone.io/) and [OpenSearch](https://opensearch.org/) or build your own indices on top of the same of [FineWeb Sample-10BT](https://huggingface.co/datasets/HuggingFaceFW/fineweb/viewer/sample-10BT) corpus
|
35 |
1. To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)
|
36 |
+
2. To build your own **OpenSearch** index, create or use your existing AWS account and apply the provided AWS credits to save costs (see [here](Operational_Instructions/AWS_Accounts_for_LiveRAG.md))
|
37 |
3. To build your own **Pinecone** index, create or use your existing Pinecone account and apply the provided Pinecone credits to save costs (see [here](Operational_Instructions/Pinecone_for_LiveRAG.md))
|
38 |
|
39 |
## 2.2 Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform
|
|
|
44 |
3.2 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))
|
45 |
**Remark:** Accessing Falcon via the AI71-Platform API is optional and recommended for a quick start. However, for a robust solution, suitable for the live event, it is recommended to set up your own Falcon3-10B-Instruct instance
|
46 |
|
47 |
+
## 2.3. Building, training, and evaluating your RAG system
|
48 |
1. Build your RAG system in your AWS Team account leveraging your FineWeb indices - make sure to use Falcon3-10B-Instruct to generate answers
|
49 |
2. Train your RAG system using synthetic Q&A pairs generated by DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb)
|
50 |
3. Evaluate your RAG system using the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md)
|
51 |
|
52 |
+
## 4. LiveRAG Challenge day details will be added soon...
|
53 |
|
54 |
You may contact the organizers via:
|
55 |
- sigir2025-liverag-gen@tii.ae - for general issues
|