yoelle commited on
Commit
2ba526d
Β·
verified Β·
1 Parent(s): 4cb3124

Update LiveRAG_README.md

Browse files
Files changed (1) hide show
  1. LiveRAG_README.md +19 -10
LiveRAG_README.md CHANGED
@@ -1,23 +1,32 @@
1
  # πŸš€ LiveRAG Challenge Operational Instructions
 
 
 
 
 
 
 
 
 
 
2
  ---
3
  ## πŸ‘£ LiveRAG Challenge Step-by-Step Guide
4
 
5
  1. Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform\
6
- 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
7
- 1.2 After you're notified that you have clearance, login to your [AI71-Platform account](https://platform.ai71.ai)\
8
- 1.2.1 Access the DataMorgana [Sandbox](https://platform.ai71.ai/playground) and [try it](Operational_Instructions/DM_Sandbox.md) to get your first Q&A\
9
- 1.2.2 Create your AI71-Platform [API key](https://platform.ai71.ai/api-keys)\
10
- 1.3 Use your AI71-Platform key for programatic access to DataMorgana bulk requests generation via its [API](Operational_Instructions/DM_API_usage_example.ipynb)\
11
- 1.4 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))\
12
  **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
13
 
14
- 3. Using [Pinecone](https://www.pinecone.io/) and [OpenSearch](https://opensearch.org/) pre-built indices of [FineWeb Sample-10BT](https://huggingface.co/datasets/HuggingFaceFW/fineweb/viewer/sample-10BT) and building your own indices\
15
  2.1 To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)\
16
  2.2 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_and_Pinecone_Accounts_for_LiveRAG.md))\
17
  2.3 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))
18
-
19
- 4. Building, training, and evaluating your RAG system\
20
- 3.1 Use your AWS private account or any other platform to build your RAG system using Falcon3-10B-Instruct\
21
  3.2 Build your own indices or use the pre-built Pinecone and OpenSearch indices\
22
  3.3 Use the DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb) to get training Q&A pairs\
23
  3.4 Follow the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md) to evaluate your RAG system
 
1
  # πŸš€ LiveRAG Challenge Operational Instructions
2
+
3
+
4
+ ## πŸ‘£ LiveRAG Challenge Onboarding
5
+
6
+
7
+ 1. Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform\
8
+ 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
9
+ 1.2 After you're notified that you are approved, login to your [AI71-Platform account](https://platform.ai71.ai)\
10
+
11
+
12
  ---
13
  ## πŸ‘£ LiveRAG Challenge Step-by-Step Guide
14
 
15
  1. Accessing DataMorgana and Falcon3-10B-Instruct via AI71-Platform\
16
+ 1.1 Login to your [AI71-Platform account](https://platform.ai71.ai)\
17
+ 1.1.1 Access the DataMorgana [Sandbox](https://platform.ai71.ai/playground) and [try it](Operational_Instructions/DM_Sandbox.md) to get your first Q&A\
18
+ 1.1.2 Create your AI71-Platform [API key](https://platform.ai71.ai/api-keys)\
19
+ 1.2 Use your AI71-Platform key for programatic access to DataMorgana bulk requests generation via its [API](Operational_Instructions/DM_API_usage_example.ipynb)\
20
+ 1.3 Use your AI71-Platform key for programatic access to Falcon3-10B-Instruct (see [AI71 documentation](https://platform.ai71.ai/documentation))\
 
21
  **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
22
 
23
+ 2. Using [Pinecone](https://www.pinecone.io/) and [OpenSearch](https://opensearch.org/) pre-built indices of [FineWeb Sample-10BT](https://huggingface.co/datasets/HuggingFaceFW/fineweb/viewer/sample-10BT) and building your own indices\
24
  2.1 To use the pre-built indices follow this [sample notebook](Operational_Instructions/Indices_Usage_Examples_for_LiveRAG.ipynb)\
25
  2.2 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_and_Pinecone_Accounts_for_LiveRAG.md))\
26
  2.3 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))
27
+
28
+ 3. Building, training, and evaluating your RAG system\
29
+ 3.1 Use your AWS team account to build your RAG system using Falcon3-10B-Instruct\
30
  3.2 Build your own indices or use the pre-built Pinecone and OpenSearch indices\
31
  3.3 Use the DataMorgana [API](Operational_Instructions/DM_API_usage_example.ipynb) to get training Q&A pairs\
32
  3.4 Follow the [evaluation guidelines](Operational_Instructions/Evaluation_Guidelines_for_LiveRAG.md) to evaluate your RAG system