In this article, we'll cover how to integrate Alibaba Cloud AI features with Elasticsearch to improve relevance in semantic searches.
Alibaba Cloud AI Search is a solution that integrates advanced AI features with Elasticsearch tools, by leveraging the Qwen LLM family to contribute with advanced models for inference and classification. In this article, we'll use descriptions of novels and plays written by the same author to test the Alibaba reranking and sparse embedding endpoints.
Steps
- Configure Alibaba Cloud AI
- Create Elasticsearch mappings
- Index data into Elasticsearch
- Query data
- Bonus: Answering questions with completion
Configure Alibaba Cloud AI
Alibaba Cloud AI reranking and embeddings
Open inference Alibaba Cloud offers different services. In this example, we'll use the descriptions of popular books and plays by Agatha Christie to test Alibaba Cloud embeddings and reranking endpoints in semantic search.
The Alibaba Cloud AI reranking endpoint is a semantic reranking functionality. This type of reranking uses a machine learning model to reorder search results based on their semantic similarity to a query. This allows you to use out-of-the-box semantic search capabilities on existing full-text search indices.
The sparse embedding endpoint is a type of embedding where most values are zero, making relevant information more prominent.
Get Alibaba Cloud API Key
We need a valid API Key to integrate Alibaba with Elasticsearch. To get it, follow these steps:
- Access the Alibaba Cloud portal from the Service Plaza section.
- Go to the left menu API Keys as shown below.
- Generate a new API Key.
Configure Alibaba Endpoints
We´ll first configure the sparse embedding endpoint to transform the text descriptions into semantic vectors:
Embeddings endpoint:
PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse
{
"service": "alibabacloud-ai-search",
"service_settings": {
"api_key": "<api_key>",
"service_id": "ops-text-sparse-embedding-001",
"host": "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com",
"workspace": "default"
}
}We´ll then configure the rerank endpoint to reorganize results.
Rerank Endpoint:
PUT _inference/rerank/alibabacloud_ai_search_rerank
{
"service": "alibabacloud-ai-search",
"service_settings": {
"api_key": "<api_key>",
"service_id": "ops-bge-reranker-larger",
"host": "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com",
"workspace": "default"
}
}Now that the endpoints are configured, we can prepare the Elasticsearch index.
Create Elasticsearch mappings
Let's configure the mappings. For this, we need to organize both the texts with the descriptions as well as the model-generated vectors.
We'll use the following properties:
- semantic_description: to store the embeddings generated by the model and run semantic searches.
- description: we'll use a "text" type to store the novels and plays’ descriptions and use them for full-text search.
We'll include the copy_to parameter so that both the text and the semantic field are available for hybrid search:
PUT arts
{
"mappings": {
"properties": {
"semantic_description": {
"type": "semantic_text",
"inference_id": "alibabacloud_ai_search_sparse"
},
"description": {
"type": "text",
"copy_to": "semantic_description"
}
}
}
}With the mappings ready, we can now index the data.
Index data into Elasticsearch
Here's the dataset with the descriptions that we'll use for this example. We'll index it using the Elasticsearch Bulk API.
POST arts/_bulk
{ "index": {} }
{ "description": " Black Coffee is a play by the British crime-fiction author Agatha Christie. In the play, a scientist discovers that someone in his household has stolen the formula for an explosive." }
{ "index": {} }
{ "description": "The Mousetrap is a murder mystery play by Agatha Christie. The play opened in London's West End in 1952 and ran continuously until 16 March 2020." }
{ "index": {} }
{ "description": "The Body in the Murder is a Miss Marple mystery novel published by Agatha Christie in 1942. The case involves the murder of two teenage girls who are similar in appearance." }
{ "index": {} }
{ "description": " Agatha Christie's last published novel before she passed, Curtain: Poirot's Last Case is also her indelible detective's last appearance. Poirot and Hastings return to the very same house from The Mysterious Affairs at Styles over 30 years later." }
{ "index": {} }
{ "description": " Death on the Nile is Agatha Christie's most daring travel mystery novel. The tranquillity of a cruise along the Nile is shattered by the discovery that Linnet Ridgeway has been shot through the head." }
{ "index": {} }
{ "description": " The Murder of Roger Ackroyd was Agatha Christie’s first book to be published by William Collins in the spring of 1926. William Collins became part of HarperCollins and are still Christie’s publishers today." }Note that the first two documents, “Black Coffee” and “The Mousetraps” are plays while the others are novels.
Query data
To see the different results we can get, we'll run different types of queries, starting with semantic query, then applying reranking, and finally using both. We'll use the same question "Which novel was written by Agatha Christie?" expecting to get the three documents that explicitly say novel, plus the one that says book. The two plays should be the last results.
Semantic search
We'll begin querying the semantic_text field to ask: "Which novel was written by Agatha Christie?" Let's see what happens:
GET /arts/_search
{
"_source": {
"includes": [
"description"
]
},
"query": {
"semantic": {
"field": "semantic_description",
"query": "Which novel was written by Agatha Christie?"
}
}
}Response:
{
"took": 1246,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 6,
"relation": "eq"
},
"max_score": 0.1759066,
"hits": [
{
"_index": "arts",
"_id": "rdJ4-ZMB36zj9EVTnMgJ",
"_score": 0.1759066,
"_source": {
"description": " Death on the Nile is Agatha Christie's most daring travel mystery novel. The tranquillity of a cruise along the Nile is shattered by the discovery that Linnet Ridgeway has been shot through the head."
}
},
{
"_index": "arts",
"_id": "rNJ4-ZMB36zj9EVTnMgJ",
"_score": 0.17499167,
"_source": {
"description": " Agatha Christie's last published novel before she passed, Curtain: Poirot's Last Case is also her indelible detective's last appearance. Poirot and Hastings return to the very same house from The Mysterious Affairs at Styles over 30 years later."
}
},
{
"_index": "arts",
"_id": "q9J4-ZMB36zj9EVTnMgJ",
"_score": 0.16319725,
"_source": {
"description": "The Body in the Murder is a Miss Marple mystery novel published by Agatha Christie in 1942. The case involves the murder of two teenage girls who are similar in appearance."
}
},
{
"_index": "arts",
"_id": "qtJ4-ZMB36zj9EVTnMgJ",
"_score": 0.15506727,
"_source": {
"description": "The Mousetrap is a murder mystery play by Agatha Christie. The play opened in London's West End in 1952 and ran continuously until 16 March 2020."
}
},
{
"_index": "arts",
"_id": "qdJ4-ZMB36zj9EVTnMgJ",
"_score": 0.14572844,
"_source": {
"description": " Black Coffee is a play by the British crime-fiction author Agatha Christie. In the play, a scientist discovers that someone in his household has stolen the formula for an explosive."
}
},
{
"_index": "arts",
"_id": "rtJ4-ZMB36zj9EVTnMgJ",
"_score": 0.13951442,
"_source": {
"description": " The Murder of Roger Ackroyd was Agatha Christie’s first book to be published by William Collins in the spring of 1926. William Collins became part of HarperCollins and are still Christie’s publishers today."
}
}
]
}
}In this case, the response prioritized most of the novels, but the document that says “book” appears last. We can still further refine the results with reranking.
Refining results with Reranking
In this case, we'll use a _inference/rerank request to assess the documents we got in the first query and improve their rank in the results.
POST _inference/rerank/alibabacloud_ai_search_rerank
{
"query": "Which novel was written by Agatha Christie?",
"input": [
"Black Coffee is a play by the British crime-fiction author Agatha Christie. In the play, a scientist discovers that someone in his household has stolen the formula for an explosive.",
"The Mousetrap is a murder mystery play by Agatha Christie. The play opened in London's West End in 1952 and ran continuously until 16 March 2020.",
" The Body in the Murder is a Miss Marple mystery novel published by Agatha Christie in 1942. The case involves the murder of two teenage girls who are similar in appearance.",
" Agatha Christie's last published novel before she passed, Curtain: Poirot's Last Case is also her indelible detective's last appearance. Poirot and Hastings return to the very same house from The Mysterious Affairs at Styles over 30 years later.",
" Death on the Nile is Agatha Christie's most daring travel mystery novel. The tranquillity of a cruise along the Nile is shattered by the discovery that Linnet Ridgeway has been shot through the head.",
" The Murder of Roger Ackroyd was Agatha Christie’s first book to be published by William Collins in the spring of 1926. William Collins became part of HarperCollins and are still Christie’s publishers today."
]
}Response:
{
"rerank": [
{
"index": 3,
"relevance_score": 0.91086304
},
{
"index": 4,
"relevance_score": 0.8409133
},
{
"index": 2,
"relevance_score": 0.76838577
},
{
"index": 5,
"relevance_score": 0.2295352
},
{
"index": 0,
"relevance_score": 0.13846178
},
{
"index": 1,
"relevance_score": 0.06620602
}
]
}The response here shows that both plays are now at the bottom of the results.
Semantic search and reranking endpoint combined
Using a retriever, we'll combine the semantic query and reranking in just one step:
POST /arts/_search
{
"_source": {
"includes": ["description"]
},
"retriever": {
"text_similarity_reranker": {
"retriever": {
"standard": {
"query": {
"semantic": {
"field": "semantic_description",
"query": "Which novel was written by Agatha Christie?"
}
}
}
},
"field": "description",
"rank_window_size": 10,
"inference_id": "alibabacloud_ai_search_rerank",
"inference_text": "Which novel was written by Agatha Christie?"
}
}
}Response:
"took": 1568,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 6,
"relation": "eq"
},
"max_score": 0.91086304,
"hits": [
{
"_index": "arts",
"_id": "rNJ4-ZMB36zj9EVTnMgJ",
"_score": 0.91086304,
"_source": {
"description": " Agatha Christie's last published novel before she passed, Curtain: Poirot's Last Case is also her indelible detective's last appearance. Poirot and Hastings return to the very same house from The Mysterious Affairs at Styles over 30 years later."
}
},
{
"_index": "arts",
"_id": "rdJ4-ZMB36zj9EVTnMgJ",
"_score": 0.8409133,
"_source": {
"description": " Death on the Nile is Agatha Christie's most daring travel mystery novel. The tranquillity of a cruise along the Nile is shattered by the discovery that Linnet Ridgeway has been shot through the head."
}
},
{
"_index": "arts",
"_id": "q9J4-ZMB36zj9EVTnMgJ",
"_score": 0.76838577,
"_source": {
"description": "The Body in the Murder is a Miss Marple mystery novel published by Agatha Christie in 1942. The case involves the murder of two teenage girls who are similar in appearance."
}
},
{
"_index": "arts",
"_id": "rtJ4-ZMB36zj9EVTnMgJ",
"_score": 0.2295352,
"_source": {
"description": " The Murder of Roger Ackroyd was Agatha Christie’s first book to be published by William Collins in the spring of 1926. William Collins became part of HarperCollins and are still Christie’s publishers today."
}
},
{
"_index": "arts",
"_id": "qdJ4-ZMB36zj9EVTnMgJ",
"_score": 0.13846178,
"_source": {
"description": " Black Coffee is a play by the British crime-fiction author Agatha Christie. In the play, a scientist discovers that someone in his household has stolen the formula for an explosive."
}
},
{
"_index": "arts",
"_id": "qtJ4-ZMB36zj9EVTnMgJ",
"_score": 0.06620602,
"_source": {
"description": "The Mousetrap is a murder mystery play by Agatha Christie. The play opened in London's West End in 1952 and ran continuously until 16 March 2020."
}
}
]
}
}The results here differ from the semantic query. We can see that the document with no exact match for "novel" but that says “book” (The Murder of Roger Ackroyd) appears higher than in the first semantic search. Both plays are still the last results, just like with reranking.
Bonus: Answering questions with completion
With embeddings and reranking we can satisfy a search query, but still, the user will see all the search results and not the actual answer.
With the examples provided, we are one step away from a RAG implementation, where we can provide the top results + the question to an LLM to get the right answer.
Fortunately, Alibaba Cloud AI Service also provides an endpoint service we can use to achieve this purpose.
Let’s create the endpoint
Completion Endpoint:
PUT _inference/completion/alibabacloud_ai_search_completion
{
"service": "alibabacloud-ai-search",
"service_settings": {
"host" : "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com",
"api_key": "<api_key>",
"service_id": "ops-qwen-turbo",
"workspace" : "default"
}
}And now, send the results and question from the previous query:
Query
POST _inference/completion/alibabacloud_ai_search_completion
{
"input": """
Answer the following question using the context provided:
QUESTION: Which novel was written by Agatha Christie?
CONTEXT:
DOCUMENT1
Black Coffee is a play by the British crime-fiction author Agatha Christie. In the play, a scientist discovers that someone in his household has stolen the formula for an explosive.
DOCUMENT2
The Mousetrap is a murder mystery play by Agatha Christie. The play opened in London's West End in 1952 and ran continuously until 16 March 2020.
DOCUMENT3
The Body in the Murder is a Miss Marple mystery novel published by Agatha Christie in 1942. The case involves the murder of two teenage girls who are similar in appearance.
DOCUMENT4
Agatha Christie's last published novel before she passed, Curtain: Poirot's Last Case is also her indelible detective's last appearance. Poirot and Hastings return to the very same house from The Mysterious Affairs at Styles over 30 years later.
DOCUMENT5
Death on the Nile is Agatha Christie's most daring travel mystery novel. The tranquillity of a cruise along the Nile is shattered by the discovery that Linnet Ridgeway has been shot through the head."
DOCUMENT6
The Murder of Roger Ackroyd was Agatha Christie’s first book to be published by William Collins in the spring of 1926. William Collins became part of HarperCollins and are still Christie’s publishers today.
ANSWER:
"""
}Response
{
"completion": [
{
"result": "Agatha Christie wrote several novels, including \"The Body in the Murder,\" \"Curtain: Poirot's Last Case,\" \"Death on the Nile,\" and \"The Murder of Roger Ackroyd.\""
}
]
}Conclusion
Integrating Alibaba Cloud AI Search with Elasticsearch allows us to easily access completion, embedding, and reranking models to incorporate them into our search pipeline.
We can use the reranking and embedding endpoints, either separately or together, with the help of a retriever.
We can also introduce the completion endpoint to finish up a RAG end-to-end implementation.
Ready to try this out on your own? Start a free trial.
Elasticsearch has integrations for tools from LangChain, Cohere and more. Join our Beyond RAG Basics webinar to build your next GenAI app!
Related content
February 28, 2025
How to ingest data to Elasticsearch through LlamaIndex
A step-by-step on how to ingest data and search using RAG with LlamaIndex.
February 25, 2025
Spotify Wrapped part 2: Diving deeper into the data
We will dive deeper into your Spotify data than ever before and explore connections you didn't even know existed.
February 24, 2025
Understanding sparse vector embeddings with trained ML models
Learn about sparse vector embeddings, understand what they do/mean, and how to implement semantic search with them.
February 19, 2025
Elasticsearch autocomplete search
Exploring different approaches to handling autocomplete, from basic to advanced, including search as you type, query time, completion suggester, and index time.
February 18, 2025
Exploring CLIP alternatives
Analyzing alternatives to the CLIP model for image-to-image, and text-to-image search.