-
Notifications
You must be signed in to change notification settings - Fork 36
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Browse files
Browse the repository at this point in the history
Adding additional default use cases (#731) * adding pretrained model templates * adding reindex * changing file structure for bwc --------- Signed-off-by: Amit Galitzky <[email protected]>
- Loading branch information
1 parent
9e0fc98
commit c4eefdd
Showing
24 changed files
with
631 additions
and
45 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
23 changes: 23 additions & 0 deletions
23
src/main/resources/defaults/hybrid-search-with-local-model-defaults.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| { | ||
| "template.name": "hybrid-search", | ||
| "template.description": "Setting up hybrid search, ingest pipeline and index", | ||
| "register_local_pretrained_model.name": "huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2", | ||
| "register_local_pretrained_model.description": "This is a sentence transformer model", | ||
| "register_local_pretrained_model.model_format": "TORCH_SCRIPT", | ||
| "register_local_pretrained_model.deploy": "true", | ||
| "register_local_pretrained_model.version": "1.0.1", | ||
| "create_ingest_pipeline.pipeline_id": "nlp-ingest-pipeline", | ||
| "create_ingest_pipeline.description": "A text embedding pipeline", | ||
| "create_ingest_pipeline.model_id": "123", | ||
| "text_embedding.field_map.input": "passage_text", | ||
| "text_embedding.field_map.output": "passage_embedding", | ||
| "create_index.name": "my-nlp-index", | ||
| "create_index.settings.number_of_shards": "2", | ||
| "create_index.mappings.method.engine": "lucene", | ||
| "create_index.mappings.method.space_type": "l2", | ||
| "create_index.mappings.method.name": "hnsw", | ||
| "text_embedding.field_map.output.dimension": "768", | ||
| "create_search_pipeline.pipeline_id": "nlp-search-pipeline", | ||
| "normalization-processor.normalization.technique": "min_max", | ||
| "normalization-processor.combination.technique": "arithmetic_mean" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
20 changes: 20 additions & 0 deletions
20
src/main/resources/defaults/semantic-search-with-local-model-defaults.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,20 @@ | ||
| { | ||
| "template.name": "semantic search with local pretrained model", | ||
| "template.description": "Setting up semantic search, with a local pretrained embedding model", | ||
| "register_local_pretrained_model.name": "huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2", | ||
| "register_local_pretrained_model.description": "This is a sentence transformer model", | ||
| "register_local_pretrained_model.model_format": "TORCH_SCRIPT", | ||
| "register_local_pretrained_model.deploy": "true", | ||
| "register_local_pretrained_model.version": "1.0.1", | ||
| "create_ingest_pipeline.pipeline_id": "nlp-ingest-pipeline", | ||
| "create_ingest_pipeline.description": "A text embedding pipeline", | ||
| "text_embedding.field_map.input": "passage_text", | ||
| "text_embedding.field_map.output": "passage_embedding", | ||
| "create_index.name": "my-nlp-index", | ||
| "create_index.settings.number_of_shards": "2", | ||
| "create_index.mappings.method.engine": "lucene", | ||
| "create_index.mappings.method.space_type": "l2", | ||
| "create_index.mappings.method.name": "hnsw", | ||
| "text_embedding.field_map.output.dimension": "768", | ||
| "create_search_pipeline.pipeline_id": "default_model_pipeline" | ||
| } |
31 changes: 31 additions & 0 deletions
31
src/main/resources/defaults/semantic-search-with-reindex-defaults.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,31 @@ | ||
| { | ||
| "template.name": "semantic search with cohere embedding", | ||
| "template.description": "Setting up semantic search, with a Cohere embedding model", | ||
| "create_connector.name": "cohere-embedding-connector", | ||
| "create_connector.description": "The connector to Cohere's public embed API", | ||
| "create_connector.protocol": "http", | ||
| "create_connector.model": "embed-english-v3.0", | ||
| "create_connector.input_type": "search_document", | ||
| "create_connector.truncate": "end", | ||
| "create_connector.credential.key": "123", | ||
| "create_connector.actions.url": "https://api.cohere.ai/v1/embed", | ||
| "create_connector.actions.request_body": "{ \"texts\": ${parameters.texts}, \"truncate\": \"${parameters.truncate}\", \"model\": \"${parameters.model}\", \"input_type\": \"${parameters.input_type}\" }", | ||
| "create_connector.actions.pre_process_function": "connector.pre_process.cohere.embedding", | ||
| "create_connector.actions.post_process_function": "connector.post_process.cohere.embedding", | ||
| "register_remote_model.name": "Cohere english embed model", | ||
| "register_remote_model.description": "cohere-embedding-model", | ||
| "create_ingest_pipeline.pipeline_id": "nlp-ingest-pipeline", | ||
| "create_ingest_pipeline.description": "A text embedding pipeline", | ||
| "text_embedding.field_map.input": "passage_text", | ||
| "text_embedding.field_map.output": "passage_embedding", | ||
| "create_index.name": "my-nlp-index", | ||
| "create_index.settings.number_of_shards": "2", | ||
| "create_index.mappings.method.engine": "lucene", | ||
| "create_index.mappings.method.space_type": "l2", | ||
| "create_index.mappings.method.name": "hnsw", | ||
| "text_embedding.field_map.output.dimension": "1024", | ||
| "create_search_pipeline.pipeline_id": "default_model_pipeline", | ||
| "reindex.source_index": "", | ||
| "reindex.requests_per_second": "-1", | ||
| "reindex.slices": "1" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
109 changes: 109 additions & 0 deletions
109
src/main/resources/substitutionTemplates/hybrid-search-with-local-model-template.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
| { | ||
| "name": "${{template.name}}", | ||
| "description": "${{template.description}}", | ||
| "use_case": "HYBRID_SEARCH", | ||
| "version": { | ||
| "template": "1.0.0", | ||
| "compatibility": [ | ||
| "2.12.0", | ||
| "3.0.0" | ||
| ] | ||
| }, | ||
| "workflows": { | ||
| "provision": { | ||
| "nodes": [ | ||
| { | ||
| "id": "register_local_pretrained_model", | ||
| "type": "register_local_pretrained_model", | ||
| "user_inputs": { | ||
| "name": "${{register_local_pretrained_model.name}}", | ||
| "version": "${{register_local_pretrained_model.version}}", | ||
| "description": "${{register_local_pretrained_model.description}}", | ||
| "model_format": "${{register_local_pretrained_model.model_format}}", | ||
| "deploy": true | ||
| } | ||
| }, | ||
| { | ||
| "id": "create_ingest_pipeline", | ||
| "type": "create_ingest_pipeline", | ||
| "previous_node_inputs": { | ||
| "register_local_pretrained_model": "model_id" | ||
| }, | ||
| "user_inputs": { | ||
| "pipeline_id": "${{create_ingest_pipeline.pipeline_id}}", | ||
| "configurations": { | ||
| "description": "${{create_ingest_pipeline.description}}", | ||
| "processors": [ | ||
| { | ||
| "text_embedding": { | ||
| "model_id": "${{register_local_pretrained_model.model_id}}", | ||
| "field_map": { | ||
| "${{text_embedding.field_map.input}}": "${{text_embedding.field_map.output}}" | ||
| } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "id": "create_index", | ||
| "type": "create_index", | ||
| "previous_node_inputs": { | ||
| "create_ingest_pipeline": "pipeline_id" | ||
| }, | ||
| "user_inputs": { | ||
| "index_name": "${{create_index.name}}", | ||
| "configurations": { | ||
| "settings": { | ||
| "index.knn": true, | ||
| "default_pipeline": "${{create_ingest_pipeline.pipeline_id}}", | ||
| "number_of_shards": "${{create_index.settings.number_of_shards}}", | ||
| "index.search.default_pipeline": "${{create_search_pipeline.pipeline_id}}" | ||
| }, | ||
| "mappings": { | ||
| "properties": { | ||
| "${{text_embedding.field_map.output}}": { | ||
| "type": "knn_vector", | ||
| "dimension": "${{text_embedding.field_map.output.dimension}}", | ||
| "method": { | ||
| "engine": "${{create_index.mappings.method.engine}}", | ||
| "space_type": "${{create_index.mappings.method.space_type}}", | ||
| "name": "${{create_index.mappings.method.name}}", | ||
| "parameters": {} | ||
| } | ||
| }, | ||
| "${{text_embedding.field_map.input}}": { | ||
| "type": "text" | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "id": "create_search_pipeline", | ||
| "type": "create_search_pipeline", | ||
| "user_inputs": { | ||
| "pipeline_id": "${{create_search_pipeline.pipeline_id}}", | ||
| "configurations": { | ||
| "description": "Post processor for hybrid search", | ||
| "phase_results_processors": [ | ||
| { | ||
| "normalization-processor": { | ||
| "normalization": { | ||
| "technique": "${{normalization-processor.normalization.technique}}" | ||
| }, | ||
| "combination": { | ||
| "technique": "${{normalization-processor.combination.technique}}" | ||
| } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.