Spaces:
Sleeping
Sleeping
Update LiveRAG_README.md
Browse files- LiveRAG_README.md +18 -14
LiveRAG_README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
# π LiveRAG Challenge Operational Instructions
|
2 |
|
3 |
|
|
|
|
|
4 |
## π£ LiveRAG Challenge Onboarding
|
5 |
|
6 |
|
@@ -8,15 +10,17 @@
|
|
8 |
1. Setting up your AWS accounts\
|
9 |
1.1 Accessing the AWS LiveRAG account - follow the instructions you received by email\
|
10 |
1.2 Applying your AWS credits to your team account - follow the instructions you received by email\
|
11 |
-
**
|
|
|
|
|
12 |
|
13 |
-
|
14 |
2.1 Sign up for a [Pinecone](https://pinecone.io ) account, adding a payment method (upgrade to standard). You will not be charged at this time\
|
15 |
2.2 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\
|
16 |
**Remark:** Do you use Pinecone servcies until you see the allocated credits appear in your account, otherwise you will be charged
|
17 |
|
18 |
|
19 |
-
|
20 |
1.1 Register to [AI71-Platform](https://platform.ai71.ai/register) and send the email address used for registration to sigir2025-liverag-tech@tii.ae\
|
21 |
1.2 After you're notified that you are approved, login to your [AI71-Platform account](https://platform.ai71.ai)
|
22 |
|
@@ -25,29 +29,29 @@
|
|
25 |
## π£ LiveRAG Challenge Step-by-Step Guide
|
26 |
|
27 |
1. Accessing or building your RAG indices\
|
28 |
-
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
|
29 |
-
1.1 To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)
|
30 |
1.2 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))\
|
31 |
1.3 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))
|
32 |
|
33 |
-
2. Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform
|
34 |
-
2.1 Login to your [AI71-Platform account](https://platform.ai71.ai) after you followed the onboarding instructions
|
35 |
2.2 Access the DataMorgana [Sandbox](https://platform.ai71.ai/playground) and [try it](Operational_Instructions/DM_Sandbox.md) to get your first Q&A\
|
36 |
-
2.3 Create your AI71-Platform [API key](https://platform.ai71.ai/api-keys)
|
37 |
2.3.1 Use your AI71-Platform key for programatic access to DataMorgana bulk requests generation via its [API](Operational_Instructions/DM_API_usage_example.ipynb)\
|
38 |
2.3.2 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))\
|
39 |
**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
|
40 |
|
41 |
3.Building, training, and evaluating your RAG system\
|
42 |
-
3.1 Build your RAG system in your AWS Team account leveraging your FineWeb indices - make sure to use Falcon3-10B-Instruct to generate answers
|
43 |
-
3.2 Train your RAG system using synthetic Q&A pairs generated by DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb)
|
44 |
-
3.3 Evaluate your RAG system using the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md)
|
45 |
|
46 |
4. LiveRAG live event details will be added soon...
|
47 |
|
48 |
-
You may contact the organizers via
|
49 |
-
|
50 |
-
|
51 |
|
52 |
---
|
53 |
## π DataMorgana
|
|
|
1 |
# π LiveRAG Challenge Operational Instructions
|
2 |
|
3 |
|
4 |
+
|
5 |
+
|
6 |
## π£ LiveRAG Challenge Onboarding
|
7 |
|
8 |
|
|
|
10 |
1. Setting up your AWS accounts\
|
11 |
1.1 Accessing the AWS LiveRAG account - follow the instructions you received by email\
|
12 |
1.2 Applying your AWS credits to your team account - follow the instructions you received by email\
|
13 |
+
**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.
|
14 |
+
|
15 |
+
**Remark:** Additional details are provided in [AWS Accounts instructions](Operational_Instructions/AWS_Accounts_for_LiveRAG.md)
|
16 |
|
17 |
+
3. Setting your Pinecone account if you want to build your own dense index\
|
18 |
2.1 Sign up for a [Pinecone](https://pinecone.io ) account, adding a payment method (upgrade to standard). You will not be charged at this time\
|
19 |
2.2 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\
|
20 |
**Remark:** Do you use Pinecone servcies until you see the allocated credits appear in your account, otherwise you will be charged
|
21 |
|
22 |
|
23 |
+
4. Register to AI71-Platform to access DataMorgana and Falcon3-10B-Instruct LLM\
|
24 |
1.1 Register to [AI71-Platform](https://platform.ai71.ai/register) and send the email address used for registration to sigir2025-liverag-tech@tii.ae\
|
25 |
1.2 After you're notified that you are approved, login to your [AI71-Platform account](https://platform.ai71.ai)
|
26 |
|
|
|
29 |
## π£ LiveRAG Challenge Step-by-Step Guide
|
30 |
|
31 |
1. Accessing or building your RAG indices\
|
32 |
+
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
|
33 |
+
1.1 To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)
|
34 |
1.2 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))\
|
35 |
1.3 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))
|
36 |
|
37 |
+
2. Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform
|
38 |
+
2.1 Login to your [AI71-Platform account](https://platform.ai71.ai) after you followed the onboarding instructions
|
39 |
2.2 Access the DataMorgana [Sandbox](https://platform.ai71.ai/playground) and [try it](Operational_Instructions/DM_Sandbox.md) to get your first Q&A\
|
40 |
+
2.3 Create your AI71-Platform [API key](https://platform.ai71.ai/api-keys)
|
41 |
2.3.1 Use your AI71-Platform key for programatic access to DataMorgana bulk requests generation via its [API](Operational_Instructions/DM_API_usage_example.ipynb)\
|
42 |
2.3.2 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))\
|
43 |
**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
|
44 |
|
45 |
3.Building, training, and evaluating your RAG system\
|
46 |
+
3.1 Build your RAG system in your AWS Team account leveraging your FineWeb indices - make sure to use Falcon3-10B-Instruct to generate answers
|
47 |
+
3.2 Train your RAG system using synthetic Q&A pairs generated by DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb)
|
48 |
+
3.3 Evaluate your RAG system using the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md)
|
49 |
|
50 |
4. LiveRAG live event details will be added soon...
|
51 |
|
52 |
+
You may contact the organizers via:
|
53 |
+
- sigir2025-liverag-gen@tii.ae - for general issues
|
54 |
+
- sigir2025-liverag-tech@tii.ae - for technical issues
|
55 |
|
56 |
---
|
57 |
## π DataMorgana
|