Skip to content

Commit 3d9f0b6

Browse files
teetanghVirajAgarwal1
teetangh
and
VirajAgarwal1
authored
Migrate awsbedrock to new search terminology (#91)
* Migrate awsbedrock from fts/gsi to search_based/query_based terminology - Renamed fts/ to search_based/ - Renamed gsi/ to query_based/ - Updated notebook terminology (FTS -> Search Vector Index, GSI -> Hyperscale and Composite Vector Index) - Updated frontmatter (path, title, tags, alt_paths) - Updated cross-reference links between tutorials * Update tutorial content and frontmatter for RAG with Couchbase and Amazon Bedrock - Changed the short title in frontmatter for clarity. - Updated markdown cells in Jupyter notebooks to improve formatting and consistency. - Enhanced introductory sections to better describe the tutorial's purpose and usage. - Ensured all references to Couchbase and Amazon Bedrock are accurate and up-to-date. * Fix GSI terminology: replace GSI references with query-based/Hyperscale throughout awsbedrock * Fix frontmatter titles to under 72 chars and fix 'this this' typo * Enhance formatting and structure in RAG with Couchbase and Bedrock tutorial - Updated markdown cells in the Jupyter notebook for improved readability and consistency. - Reformatted introductory sections to provide clearer guidance on building a semantic search engine. - Ensured all content is beginner-friendly and accurately describes the tutorial's objectives. * Refactor markdown cells for improved clarity and structure in RAG tutorial - Enhanced formatting of markdown cells in the Jupyter notebook for better readability. - Added line breaks for improved visual separation of content. - Ensured consistency in the presentation of tutorial instructions and prerequisites. * Update RAG tutorials with enhanced markdown clarity and updated timestamps - Revised markdown cells for improved clarity and structure in the Jupyter notebooks. - Updated timestamps in log outputs to reflect recent execution dates. - Enhanced descriptions of embedding creation and caching mechanisms for better understanding of the tutorial's objectives. * Update awsbedrock/search_based/frontmatter.md Co-authored-by: Viraj Agarwal <91372648+VirajAgarwal1@users.noreply.github.com> * reran the tutorial after deleting the existing index * Update tutorial frontmatter and content to reflect changes in language model and index type - Revised short titles in frontmatter for clarity. - Updated descriptions to replace references to the Claude language model with Nova Pro. - Enhanced markdown content in the Jupyter notebook for improved readability and structure. --------- Co-authored-by: Viraj Agarwal <91372648+VirajAgarwal1@users.noreply.github.com>
1 parent 75b0031 commit 3d9f0b6

9 files changed

Lines changed: 1403 additions & 1239 deletions

‎awsbedrock/fts/frontmatter.md‎

Lines changed: 0 additions & 22 deletions
This file was deleted.

‎awsbedrock/gsi/RAG_with_Couchbase_and_Bedrock.ipynb‎

Lines changed: 0 additions & 1077 deletions
This file was deleted.

awsbedrock/gsi/.env.sample renamed to awsbedrock/query_based/.env.sample

File renamed without changes.

‎awsbedrock/query_based/RAG_with_Couchbase_and_Bedrock.ipynb‎

Lines changed: 1184 additions & 0 deletions
Large diffs are not rendered by default.

‎awsbedrock/query_based/frontmatter.md‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
---
2+
# frontmatter
3+
path: "/tutorial-aws-bedrock-couchbase-rag-with-hyperscale-or-composite-vector-index"
4+
title: RAG with Bedrock using Couchbase Hyperscale and Composite Vector Index
5+
short_title: Amazon Bedrock RAG with Hyperscale/Composite Index
6+
description:
7+
- Learn how to build a semantic search engine using Couchbase and Amazon Bedrock using Hyperscale and Composite Vector Index.
8+
- This tutorial demonstrates how to integrate Couchbase's vector search capabilities with Amazon Bedrock's Titan embeddings and Nova Pro language model.
9+
- You'll understand how to perform Retrieval-Augmented Generation (RAG) using LangChain and Couchbase.
10+
content_type: tutorial
11+
filter: sdk
12+
technology:
13+
- vector search
14+
tags:
15+
- Hyperscale Vector Index
16+
- Composite Vector Index
17+
- Artificial Intelligence
18+
- LangChain
19+
- Amazon Bedrock
20+
sdk_language:
21+
- python
22+
length: 60 Mins
23+
alt_paths: ["/tutorial-aws-bedrock-couchbase-rag-with-hyperscale-vector-index", "/tutorial-aws-bedrock-couchbase-rag-with-composite-vector-index"]
24+
---

awsbedrock/fts/.env.sample renamed to awsbedrock/search_based/.env.sample

File renamed without changes.

awsbedrock/fts/RAG_with_Couchbase_and_Bedrock.ipynb renamed to awsbedrock/search_based/RAG_with_Couchbase_and_Bedrock.ipynb

Lines changed: 116 additions & 134 deletions
Large diffs are not rendered by default.

‎awsbedrock/search_based/aws_index.json‎

Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,73 @@
1+
{
2+
"type": "fulltext-index",
3+
"name": "vector_search_bedrock",
4+
"uuid": "",
5+
"sourceType": "gocbcore",
6+
"sourceName": "vector-search-testing",
7+
"planParams": {
8+
"maxPartitionsPerPIndex": 64,
9+
"indexPartitions": 16
10+
},
11+
"params": {
12+
"doc_config": {
13+
"docid_prefix_delim": "",
14+
"docid_regexp": "",
15+
"mode": "scope.collection.type_field",
16+
"type_field": "type"
17+
},
18+
"mapping": {
19+
"analysis": {},
20+
"default_analyzer": "standard",
21+
"default_datetime_parser": "dateTimeOptional",
22+
"default_field": "_all",
23+
"default_mapping": {
24+
"dynamic": true,
25+
"enabled": false
26+
},
27+
"default_type": "_default",
28+
"docvalues_dynamic": false,
29+
"index_dynamic": true,
30+
"store_dynamic": false,
31+
"type_field": "_type",
32+
"types": {
33+
"shared.bedrock": {
34+
"dynamic": true,
35+
"enabled": true,
36+
"properties": {
37+
"embedding": {
38+
"dynamic": false,
39+
"enabled": true,
40+
"fields": [
41+
{
42+
"dims": 1024,
43+
"index": true,
44+
"name": "embedding",
45+
"similarity": "dot_product",
46+
"type": "vector",
47+
"vector_index_optimized_for": "recall"
48+
}
49+
]
50+
},
51+
"text": {
52+
"dynamic": false,
53+
"enabled": true,
54+
"fields": [
55+
{
56+
"index": true,
57+
"name": "text",
58+
"store": true,
59+
"type": "text"
60+
}
61+
]
62+
}
63+
}
64+
}
65+
}
66+
},
67+
"store": {
68+
"indexType": "scorch",
69+
"segmentVersion": 16
70+
}
71+
},
72+
"sourceParams": {}
73+
}

awsbedrock/gsi/frontmatter.md renamed to awsbedrock/search_based/frontmatter.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,18 @@
11
---
22
# frontmatter
3-
path: "/tutorial-aws-bedrock-couchbase-rag-with-global-secondary-index"
4-
title: Retrieval-Augmented Generation (RAG) with Couchbase and Amazon Bedrock using GSI index
5-
short_title: RAG with Couchbase and Amazon Bedrock using GSI index
3+
path: "/tutorial-aws-bedrock-couchbase-rag-with-search-vector-index"
4+
title: RAG with Amazon Bedrock using Couchbase Search Vector Index
5+
short_title: RAG with Bedrock using Couchbase Search Vector Index
66
description:
7-
- Learn how to build a semantic search engine using Couchbase and Amazon Bedrock using GSI.
8-
- This tutorial demonstrates how to integrate Couchbase's vector search capabilities with Amazon Bedrock's Titan embeddings and Claude language model.
7+
- Learn how to build a semantic search engine using Couchbase and Amazon Bedrock using Search Vector Index.
8+
- This tutorial demonstrates how to integrate Couchbase's vector search capabilities with Amazon Bedrock's Titan embeddings and Nova Pro language model.
99
- You'll understand how to perform Retrieval-Augmented Generation (RAG) using LangChain and Couchbase.
1010
content_type: tutorial
1111
filter: sdk
1212
technology:
1313
- vector search
1414
tags:
15-
- GSI
15+
- Search Vector Index
1616
- Artificial Intelligence
1717
- LangChain
1818
- Amazon Bedrock

0 commit comments

Comments
 (0)