|
25 | 25 | Refer to https://docs.cohere.com/docs/elasticsearch-and-cohere[Cohere's tutorial]
|
26 | 26 | for an example using a different data set.
|
27 | 27 |
|
| 28 | +You can also review the https://colab.research.google.com/github/elastic/elasticsearch-labs/blob/main/notebooks/integrations/cohere/cohere-elasticsearch.ipynb[Colab notebook version of this tutorial]. |
| 29 | + |
28 | 30 |
|
29 | 31 | [discrete]
|
30 | 32 | [[cohere-es-req]]
|
31 | 33 | ==== Requirements
|
32 | 34 |
|
33 |
| -* A https://cohere.com/[Cohere account], |
34 |
| -* an https://www.elastic.co/guide/en/cloud/current/ec-getting-started.html[Elastic Cloud] |
35 |
| -account, |
| 35 | +* A paid https://cohere.com/[Cohere account] is required to use the {infer-cap} API with the Cohere service as the Cohere free trial API usage is limited, |
| 36 | +* an https://www.elastic.co/guide/en/cloud/current/ec-getting-started.html[Elastic Cloud] account, |
36 | 37 | * Python 3.7 or higher.
|
37 | 38 |
|
38 | 39 |
|
@@ -329,17 +330,12 @@ they were sent to the {infer} endpoint.
|
329 | 330 | [[cohere-es-rag]]
|
330 | 331 | ==== Retrieval Augmented Generation (RAG) with Cohere and {es}
|
331 | 332 |
|
332 |
| -RAG is a method for generating text using additional information fetched from an |
333 |
| -external data source. With the ranked results, you can build a RAG system on the |
334 |
| -top of what you previously created by using |
335 |
| -https://docs.cohere.com/docs/chat-api[Cohere's Chat API]. |
| 333 | +https://docs.cohere.com/docs/retrieval-augmented-generation-rag[RAG] is a method for generating text using additional information fetched from an external data source. |
| 334 | +With the ranked results, you can build a RAG system on the top of what you previously created by using https://docs.cohere.com/docs/chat-api[Cohere's Chat API]. |
336 | 335 |
|
337 |
| -Pass in the retrieved documents and the query to receive a grounded response |
338 |
| -using Cohere's newest generative model |
339 |
| -https://docs.cohere.com/docs/command-r-plus[Command R+]. |
| 336 | +Pass in the retrieved documents and the query to receive a grounded response using Cohere's newest generative model https://docs.cohere.com/docs/command-r-plus[Command R+]. |
340 | 337 |
|
341 |
| -Then pass in the query and the documents to the Chat API, and print out the |
342 |
| -response. |
| 338 | +Then pass in the query and the documents to the Chat API, and print out the response. |
343 | 339 |
|
344 | 340 | [source,py]
|
345 | 341 | --------------------------------------------------
|
|
0 commit comments