Skip to content

Commit c530ddc

Browse files
JoanFMJoanFM
committed
add documentation for jinaai service
1 parent f2e5430 commit c530ddc

File tree

2 files changed

+255
-1
lines changed

2 files changed

+255
-1
lines changed

‎docs/reference/inference/put-inference.asciidoc‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,6 +72,7 @@ Click the links to review the configuration details of the services:
7272
* <<infer-service-mistral,Mistral>> (`text_embedding`)
7373
* <<infer-service-openai,OpenAI>> (`completion`, `text_embedding`)
7474
* <<infer-service-watsonx-ai>> (`text_embedding`)
75+
* <<infer-service-jinaai,JinaAI>> (`text_embedding`, `rerank`)
7576

7677
The {es} and ELSER services run on a {ml} node in your {es} cluster. The rest of
7778
the services connect to external providers.
@@ -87,4 +88,4 @@ When adaptive allocations are enabled:
8788
- The number of allocations scales up automatically when the load increases.
8889
- Allocations scale down to a minimum of 0 when the load decreases, saving resources.
8990

90-
For more information about adaptive allocations and resources, refer to the {ml-docs}/ml-nlp-auto-scale.html[trained model autoscaling] documentation.
91+
For more information about adaptive allocations and resources, refer to the {ml-docs}/ml-nlp-auto-scale.html[trained model autoscaling] documentation.

‎docs/reference/inference/service-jinaai.asciidoc‎

Lines changed: 253 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,253 @@
1+
[[infer-service-jinaai]]
2+
=== JinaAI {infer} service
3+
4+
Creates an {infer} endpoint to perform an {infer} task with the `jinaai` service.
5+
6+
7+
[discrete]
8+
[[infer-service-jinaai-api-request]]
9+
==== {api-request-title}
10+
11+
`PUT /_inference/<task_type>/<inference_id>`
12+
13+
[discrete]
14+
[[infer-service-jinaai-api-path-params]]
15+
==== {api-path-parms-title}
16+
17+
`<inference_id>`::
18+
(Required, string)
19+
include::inference-shared.asciidoc[tag=inference-id]
20+
21+
`<task_type>`::
22+
(Required, string)
23+
include::inference-shared.asciidoc[tag=task-type]
24+
+
25+
--
26+
Available task types:
27+
28+
* `text_embedding`,
29+
* `rerank`.
30+
--
31+
32+
[discrete]
33+
[[infer-service-jinaai-api-request-body]]
34+
==== {api-request-body-title}
35+
36+
`chunking_settings`::
37+
(Optional, object)
38+
include::inference-shared.asciidoc[tag=chunking-settings]
39+
40+
`max_chunking_size`:::
41+
(Optional, integer)
42+
include::inference-shared.asciidoc[tag=chunking-settings-max-chunking-size]
43+
44+
`overlap`:::
45+
(Optional, integer)
46+
include::inference-shared.asciidoc[tag=chunking-settings-overlap]
47+
48+
`sentence_overlap`:::
49+
(Optional, integer)
50+
include::inference-shared.asciidoc[tag=chunking-settings-sentence-overlap]
51+
52+
`strategy`:::
53+
(Optional, string)
54+
include::inference-shared.asciidoc[tag=chunking-settings-strategy]
55+
56+
`service`::
57+
(Required, string)
58+
The type of service supported for the specified task type. In this case,
59+
`jinaai`.
60+
61+
`service_settings`::
62+
(Required, object)
63+
include::inference-shared.asciidoc[tag=service-settings]
64+
+
65+
--
66+
These settings are specific to the `jinaai` service.
67+
--
68+
69+
`api_key`:::
70+
(Required, string)
71+
A valid API key of your JinaAI account.
72+
You can find in:
73+
https://jina.ai/embeddings/.
74+
+
75+
--
76+
include::inference-shared.asciidoc[tag=api-key-admonition]
77+
--
78+
79+
`rate_limit`:::
80+
(Optional, object)
81+
By default, the `jinaai` service sets the number of requests allowed per minute to `2000`.
82+
This value is the same for all task types.
83+
To modify this, set the `requests_per_minute` setting of this object in your service settings:
84+
+
85+
--
86+
include::inference-shared.asciidoc[tag=request-per-minute-example]
87+
88+
More information about JinaAI's rate limits can be found in https://jina.ai/contact-sales/#rate-limit.
89+
--
90+
+
91+
.`service_settings` for the `rerank` task type
92+
[%collapsible%closed]
93+
=====
94+
`model_id`::
95+
(Optional, string)
96+
The name of the model to use for the {infer} task.
97+
To review the available `rerank` models, refer to the
98+
https://jina.ai/reranker.
99+
=====
100+
+
101+
.`service_settings` for the `text_embedding` task type
102+
[%collapsible%closed]
103+
=====
104+
`model_id`:::
105+
(Optional, string)
106+
The name of the model to use for the {infer} task.
107+
To review the available `text_embedding` models, refer to the
108+
https://jina.ai/embeddings/.
109+
110+
`similarity`:::
111+
(Optional, string)
112+
Similarity measure. One of `cosine`, `dot_product`, `l2_norm`.
113+
Defaults based on the `embedding_type` (`float` -> `dot_product`, `int8/byte` -> `cosine`).
114+
=====
115+
116+
117+
118+
`task_settings`::
119+
(Optional, object)
120+
include::inference-shared.asciidoc[tag=task-settings]
121+
+
122+
.`task_settings` for the `rerank` task type
123+
[%collapsible%closed]
124+
=====
125+
`return_documents`::
126+
(Optional, boolean)
127+
Specify whether to return doc text within the results.
128+
129+
`top_n`::
130+
(Optional, integer)
131+
The number of most relevant documents to return, defaults to the number of the documents.
132+
If this {infer} endpoint is used in a `text_similarity_reranker` retriever query and `top_n` is set, it must be greater than or equal to `rank_window_size` in the query.
133+
=====
134+
+
135+
.`task_settings` for the `text_embedding` task type
136+
[%collapsible%closed]
137+
=====
138+
`task`:::
139+
(Optional, string)
140+
Specifies the task passed to the model.
141+
Valid values are:
142+
* `classification`: use it for embeddings passed through a text classifier.
143+
* `clustering`: use it for the embeddings run through a clustering algorithm.
144+
* `ingest`: use it for storing document embeddings in a vector database.
145+
* `search`: use it for storing embeddings of search queries run against a vector database to find relevant documents.
146+
=====
147+
148+
149+
[discrete]
150+
[[inference-example-jinaai]]
151+
==== JinaAI service examples
152+
153+
The following example shows how to create {infer} endpoints to get `text_embeddings` and `rerank` and to use them in a search application.
154+
155+
First, we create the `embeddings` service:
156+
157+
[source,console]
158+
------------------------------------------------------------
159+
PUT _inference/text_embedding/jinaai-embeddings
160+
{
161+
"service": "jinaai",
162+
"service_settings": {
163+
"model_id": "jina-embeddings-v3",
164+
"api_key": "<api_key>",
165+
},
166+
"task_settings": {}
167+
}
168+
------------------------------------------------------------
169+
170+
Then, we create the `rerank` service:
171+
[source,console]
172+
------------------------------------------------------------
173+
PUT _inference/rerank/jinaai-rerank
174+
{
175+
"service": "jinaai",
176+
"service_settings": {
177+
"api_key": "<API-KEY>",
178+
"model_id": "jina-reranker-v2-base-multilingual"
179+
},
180+
"task_settings": {
181+
"top_n": 10,
182+
"return_documents": true
183+
}
184+
}
185+
------------------------------------------------------------
186+
187+
Now we can create an index that will use `jinaai-embeddings` service to index the documents.
188+
189+
[source,console]
190+
------------------------------------------------------------
191+
PUT jinaai-index
192+
{
193+
"mappings": {
194+
"properties": {
195+
"content": {
196+
"type": "semantic_text",
197+
"inference_id": "jinaai-embeddings"
198+
}
199+
}
200+
}
201+
}
202+
------------------------------------------------------------
203+
204+
[source,console]
205+
------------------------------------------------------------
206+
PUT jinaai-index/_bulk
207+
{ "index" : { "_index" : "jinaai-index", "_id" : "1" } }
208+
{"content": "Sarah Johnson is a talented marine biologist working at the Oceanographic Institute. Her groundbreaking research on coral reef ecosystems has garnered international attention and numerous accolades."}
209+
{ "index" : { "_index" : "jinaai-index", "_id" : "2" } }
210+
{"content": "She spends months at a time diving in remote locations, meticulously documenting the intricate relationships between various marine species. "}
211+
{ "index" : { "_index" : "jinaai-index", "_id" : "3" } }
212+
{"content": "Her dedication to preserving these delicate underwater environments has inspired a new generation of conservationists."}
213+
------------------------------------------------------------
214+
215+
Now, with the index created, we can search with and without the reranker service.
216+
217+
[source,console]
218+
------------------------------------------------------------
219+
GET jinaai-index/_search
220+
{
221+
"query": {
222+
"semantic": {
223+
"field": "content",
224+
"query": "who inspired taking care of the sea?"
225+
}
226+
}
227+
}
228+
------------------------------------------------------------
229+
230+
[source,console]
231+
------------------------------------------------------------
232+
POST jinaai-index/_search
233+
{
234+
"retriever": {
235+
"text_similarity_reranker": {
236+
"retriever": {
237+
"standard": {
238+
"query": {
239+
"semantic": {
240+
"field": "content",
241+
"query": "who inspired taking care of the sea?"
242+
}
243+
}
244+
}
245+
},
246+
"field": "content",
247+
"rank_window_size": 100,
248+
"inference_id": "jinaai-rerank",
249+
"inference_text": "who inspired taking care of the sea?"
250+
}
251+
}
252+
}
253+
------------------------------------------------------------

0 commit comments

Comments
 (0)