Tutorial: semantic search with ELSER
editTutorial: semantic search with ELSER
editElastic Learned Sparse EncodeR - or ELSER - is an NLP model trained by Elastic that enables you to perform semantic search by using sparse vector representation. Instead of literal matching on search terms, semantic search retrieves results based on the intent and the contextual meaning of a search query.
The instructions in this tutorial shows you how to use ELSER to perform semantic search on your data.
For the easiest way to perform semantic search in the Elastic Stack, refer to the semantic_text
end-to-end tutorial.
Only the first 512 extracted tokens per field are considered during semantic search with ELSER. Refer to this page for more information.
Requirements
editTo perform semantic search by using ELSER, you must have the NLP model deployed in your cluster. Refer to the ELSER documentation to learn how to download and deploy the model.
The minimum dedicated ML node size for deploying and using the ELSER model is 4 GB in Elasticsearch Service if deployment autoscaling is turned off. Turning on autoscaling is recommended because it allows your deployment to dynamically adjust resources based on demand. Better performance can be achieved by using more allocations or more threads per allocation, which requires bigger ML nodes. Autoscaling provides bigger nodes when required. If autoscaling is turned off, you must provide suitably sized nodes yourself.
Create the index mapping
editFirst, the mapping of the destination index - the index that contains the tokens that the model created based on your text - must be created.
The destination index must have a field with the sparse_vector
or rank_features
field type to index the ELSER output.
ELSER output must be ingested into a field with the sparse_vector
or rank_features
field type.
Otherwise, Elasticsearch interprets the token-weight pairs as a massive amount of fields in a document.
If you get an error similar to this: "Limit of total fields [1000] has been exceeded while adding new fields"
then the ELSER output field is not mapped properly and it has a field type different than sparse_vector
or rank_features
.
resp = client.indices.create( index="my-index", mappings={ "properties": { "content_embedding": { "type": "sparse_vector" }, "content": { "type": "text" } } }, ) print(resp)
response = client.indices.create( index: 'my-index', body: { mappings: { properties: { content_embedding: { type: 'sparse_vector' }, content: { type: 'text' } } } } ) puts response
const response = await client.indices.create({ index: "my-index", mappings: { properties: { content_embedding: { type: "sparse_vector", }, content: { type: "text", }, }, }, }); console.log(response);
PUT my-index { "mappings": { "properties": { "content_embedding": { "type": "sparse_vector" }, "content": { "type": "text" } } } }
The name of the field to contain the generated tokens. It must be referenced in the inference pipeline configuration in the next step. |
|
The field to contain the tokens is a |
|
The name of the field from which to create the sparse vector representation.
In this example, the name of the field is |
|
The field type which is text in this example. |
To learn how to optimize space, refer to the Saving disk space by excluding the ELSER tokens from document source section.
Create an ingest pipeline with an inference processor
editCreate an ingest pipeline with an inference processor to use ELSER to infer against the data that is being ingested in the pipeline.
resp = client.ingest.put_pipeline( id="elser-v2-test", processors=[ { "inference": { "model_id": ".elser_model_2", "input_output": [ { "input_field": "content", "output_field": "content_embedding" } ] } } ], ) print(resp)
response = client.ingest.put_pipeline( id: 'elser-v2-test', body: { processors: [ { inference: { model_id: '.elser_model_2', input_output: [ { input_field: 'content', output_field: 'content_embedding' } ] } } ] } ) puts response
const response = await client.ingest.putPipeline({ id: "elser-v2-test", processors: [ { inference: { model_id: ".elser_model_2", input_output: [ { input_field: "content", output_field: "content_embedding", }, ], }, }, ], }); console.log(response);
PUT _ingest/pipeline/elser-v2-test { "processors": [ { "inference": { "model_id": ".elser_model_2", "input_output": [ { "input_field": "content", "output_field": "content_embedding" } ] } } ] }
Configuration object that defines the |
Load data
editIn this step, you load the data that you later use in the inference ingest pipeline to extract tokens from it.
Use the msmarco-passagetest2019-top1000
data set, which is a subset of the MS MARCO Passage Ranking data set.
It consists of 200 queries, each accompanied by a list of relevant text passages.
All unique passages, along with their IDs, have been extracted from that data set and compiled into a
tsv file.
The msmarco-passagetest2019-top1000
dataset was not utilized to train the model.
We use this sample dataset in the tutorial because is easily accessible for demonstration purposes.
You can use a different data set to test the workflow and become familiar with it.
Download the file and upload it to your cluster using the File Uploader in the UI.
After your data is analyzed, click Override settings.
Under Edit field names, assign id
to the first column and content
to the second.
Click Apply, then Import.
Name the index test-data
, and click Import.
After the upload is complete, you will see an index named test-data
with 182,469 documents.
Ingest the data through the inference ingest pipeline
editCreate the tokens from the text by reindexing the data throught the inference pipeline that uses ELSER as the inference model.
resp = client.reindex( wait_for_completion=False, source={ "index": "test-data", "size": 50 }, dest={ "index": "my-index", "pipeline": "elser-v2-test" }, ) print(resp)
response = client.reindex( wait_for_completion: false, body: { source: { index: 'test-data', size: 50 }, dest: { index: 'my-index', pipeline: 'elser-v2-test' } } ) puts response
const response = await client.reindex({ wait_for_completion: "false", source: { index: "test-data", size: 50, }, dest: { index: "my-index", pipeline: "elser-v2-test", }, }); console.log(response);
POST _reindex?wait_for_completion=false { "source": { "index": "test-data", "size": 50 }, "dest": { "index": "my-index", "pipeline": "elser-v2-test" } }
The default batch size for reindexing is 1000. Reducing |
The call returns a task ID to monitor the progress:
resp = client.tasks.get( task_id="<task_id>", ) print(resp)
const response = await client.tasks.get({ task_id: "<task_id>", }); console.log(response);
GET _tasks/<task_id>
You can also open the Trained Models UI, select the Pipelines tab under ELSER to follow the progress.
Reindexing large datasets can take a long time. You can test this workflow using only a subset of the dataset. Do this by cancelling the reindexing process, and only generating embeddings for the subset that was reindexed. The following API request will cancel the reindexing task:
resp = client.tasks.cancel( task_id="<task_id>", ) print(resp)
const response = await client.tasks.cancel({ task_id: "<task_id>", }); console.log(response);
POST _tasks/<task_id>/_cancel
Semantic search by using the sparse_vector
query
editTo perform semantic search, use the sparse_vector
query, and provide the query text and the inference ID associated with your ELSER model.
The example below uses the query text "How to avoid muscle soreness after running?", the content_embedding
field contains the generated ELSER output:
resp = client.search( index="my-index", query={ "sparse_vector": { "field": "content_embedding", "inference_id": "my-elser-endpoint", "query": "How to avoid muscle soreness after running?" } }, ) print(resp)
const response = await client.search({ index: "my-index", query: { sparse_vector: { field: "content_embedding", inference_id: "my-elser-endpoint", query: "How to avoid muscle soreness after running?", }, }, }); console.log(response);
GET my-index/_search { "query":{ "sparse_vector":{ "field": "content_embedding", "inference_id": "my-elser-endpoint", "query": "How to avoid muscle soreness after running?" } } }
The result is the top 10 documents that are closest in meaning to your query text from the my-index
index sorted by their relevancy.
The result also contains the extracted tokens for each of the relevant search results with their weights.
Tokens are learned associations capturing relevance, they are not synonyms.
To learn more about what tokens are, refer to this page.
It is possible to exclude tokens from source, refer to this section to learn more.
"hits": { "total": { "value": 10000, "relation": "gte" }, "max_score": 26.199875, "hits": [ { "_index": "my-index", "_id": "FPr9HYsBag9jXmT8lEpI", "_score": 26.199875, "_source": { "content_embedding": { "muscular": 0.2821541, "bleeding": 0.37929374, "foods": 1.1718726, "delayed": 1.2112266, "cure": 0.6848574, "during": 0.5886185, "fighting": 0.35022718, "rid": 0.2752442, "soon": 0.2967024, "leg": 0.37649947, "preparation": 0.32974035, "advance": 0.09652356, (...) }, "id": 1713868, "model_id": ".elser_model_2", "content": "For example, if you go for a run, you will mostly use the muscles in your lower body. Give yourself 2 days to rest those muscles so they have a chance to heal before you exercise them again. Not giving your muscles enough time to rest can cause muscle damage, rather than muscle development." } }, (...) ] }
Combining semantic search with other queries
editYou can combine sparse_vector
with other queries in a compound query.
For example, use a filter clause in a Boolean or a full text query with the same (or different) query text as the sparse_vector
query.
This enables you to combine the search results from both queries.
The search hits from the sparse_vector
query tend to score higher than other
Elasticsearch queries.
Those scores can be regularized by increasing or decreasing the relevance scores of each query by using the boost
parameter.
Recall on the sparse_vector
query can be high where there is a long tail of less relevant results.
Use the min_score
parameter to prune those less relevant documents.
resp = client.search( index="my-index", query={ "bool": { "should": [ { "sparse_vector": { "field": "content_embedding", "inference_id": "my-elser-endpoint", "query": "How to avoid muscle soreness after running?", "boost": 1 } }, { "query_string": { "query": "toxins", "boost": 4 } } ] } }, min_score=10, ) print(resp)
const response = await client.search({ index: "my-index", query: { bool: { should: [ { sparse_vector: { field: "content_embedding", inference_id: "my-elser-endpoint", query: "How to avoid muscle soreness after running?", boost: 1, }, }, { query_string: { query: "toxins", boost: 4, }, }, ], }, }, min_score: 10, }); console.log(response);
GET my-index/_search { "query": { "bool": { "should": [ { "sparse_vector": { "field": "content_embedding", "inference_id": "my-elser-endpoint", "query": "How to avoid muscle soreness after running?", "boost": 1 } }, { "query_string": { "query": "toxins", "boost": 4 } } ] } }, "min_score": 10 }
Both the |
|
The |
|
The |
|
Only the results with a score equal to or higher than |
Optimizing performance
editSaving disk space by excluding the ELSER tokens from document source
editThe tokens generated by ELSER must be indexed for use in the sparse_vector query. However, it is not necessary to retain those terms in the document source. You can save disk space by using the source exclude mapping to remove the ELSER terms from the document source.
Reindex uses the document source to populate the destination index.
Once the ELSER terms have been excluded from the source, they cannot be recovered through reindexing.
Excluding the tokens from the source is a space-saving optimization that should only be applied if you are certain that reindexing will not be required in the future!
It’s important to carefully consider this trade-off and make sure that excluding the ELSER terms from the source aligns with your specific requirements and use case.
Review the
Disabling the _source
field and Including / Excluding fields from _source
sections carefully to learn more about the possible consequences of excluding the tokens from the _source
.
The mapping that excludes content_embedding
from the _source
field can be created by the following API call:
resp = client.indices.create( index="my-index", mappings={ "_source": { "excludes": [ "content_embedding" ] }, "properties": { "content_embedding": { "type": "sparse_vector" }, "content": { "type": "text" } } }, ) print(resp)
response = client.indices.create( index: 'my-index', body: { mappings: { _source: { excludes: [ 'content_embedding' ] }, properties: { content_embedding: { type: 'sparse_vector' }, content: { type: 'text' } } } } ) puts response
const response = await client.indices.create({ index: "my-index", mappings: { _source: { excludes: ["content_embedding"], }, properties: { content_embedding: { type: "sparse_vector", }, content: { type: "text", }, }, }, }); console.log(response);
PUT my-index { "mappings": { "_source": { "excludes": [ "content_embedding" ] }, "properties": { "content_embedding": { "type": "sparse_vector" }, "content": { "type": "text" } } } }
Depending on your data, the sparse_vector
query may be faster with track_total_hits: false
.
Further reading
editInteractive example
edit-
The
elasticsearch-labs
repo has an interactive example of running ELSER-powered semantic search using the Elasticsearch Python client.