You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -21,27 +24,4 @@ Here are a few common real-world applications:
21
24
|**Chatbots/RAG**| Enable natural conversations, provide context, maintain knowledge | Vector search, ML models, knowledge base integration |
22
25
|**Geospatial search**| Process location queries, sort by proximity, filter by area | Geo-mapping, spatial indexing, distance calculations |
23
26
24
-
## Core implementation decisions
25
27
26
-
% TODO add diagram
27
-
28
-
Building a search experience with {{es}} requires a number of fundamental implementation decisions:
29
-
30
-
1.[**Deployment**](/deploy-manage/index.md): Where will you run Elastic?
31
-
1.[**Ingestion**](search/ingest-for-search.md): What tools will you use to get your content into {{es}}?
32
-
1.[**Search approaches**](search/search-approaches.md): What search techniques and algorithms will you use to find relevant results?
33
-
1.**Implementation tools**: How will you write queries and interact with {{es}}?
34
-
- Which [programming language client]() matches your application?
35
-
- Which API endpoints and [query language(s)](search/querying-for-search.md) will you use to express your search logic?
36
-
37
-
Each decision builds on the previous ones, offering flexibility to mix and match approaches based on your needs.
38
-
39
-
% TODO update/add URLs
40
-
41
-
42
-
% Scope notes: surface key features buried in the search APIs, turn some of the API doc content into feature-specific tutorials needs some polish to separate use cases from technologies
43
-
44
-
% Use migrated content from existing pages that map to this page:
Copy file name to clipboardExpand all lines: solutions/search/ai-search/ai-search.md
+5Lines changed: 5 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,3 +1,8 @@
1
+
---
2
+
applies:
3
+
stack:
4
+
serverless:
5
+
---
1
6
# AI-powered search
2
7
3
8
Natural language understanding and information retrieval go hand in hand in modern search systems. Sometimes [full-text search](../full-text.md) alone isn't enough. Machine learning techniques are powerful tools for helping users find data based on intent and contextual meaning.
Copy file name to clipboardExpand all lines: solutions/search/api-quickstarts.md
+10-1Lines changed: 10 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,14 @@
1
+
---
2
+
applies:
3
+
stack:
4
+
serverless:
5
+
---
1
6
# API quickstarts
2
7
8
+
:::{tip}
9
+
Prefer working in Python? Check out our executable [Python notebooks](https://github.com/elastic/elasticsearch-labs/tree/main/notebooks#readme) in the Elasticsearch Labs repository.
10
+
::::
11
+
3
12
Use the following quickstarts to get hands-on experience with Elasticsearch APIs and tools:
4
13
5
14
-[Index and search data using Elasticsearch APIs](elasticsearch-basics-quickstart.md): Learn about indices, documents, and mappings, and perform a basic search using the Query DSL.
@@ -10,7 +19,7 @@ Use the following quickstarts to get hands-on experience with Elasticsearch APIs
10
19
-[Hybrid search](hybrid-semantic-text.md): Learn how to combine semantic search using`semantic_text` with full-text search.
11
20
-[Bring your own dense vector embeddings](vector/bring-own-vectors.md): Learn how to ingest dense vector embeddings into Elasticsearch.
12
21
13
-
:::{tip}
22
+
:::{note}
14
23
To run the quickstarts, you need a running Elasticsearch cluster. Use [`start-local`](https://github.com/elastic/start-local) to set up a fast local dev environment in Docker, together with Kibana. Run the following command in your terminal:
0 commit comments