- Precompute all embeddings using a BatchingStrategy before inserting into the vector store
This optimization improves efficiency when adding multiple documents
Related to #1261
* Consolidate usage of “db.collection.name” attribute to track table name, collection name, index name, document name, or whatever concept a vector database uses to store data. Removed “db.index” that was use sometimes instead of “db.collection.name”. This usage is in line with the OpenTelemetry Semantic Conventions.
* Configure query response content to be included as a “span event” instead of a “span attribute” if the backend system supports that, similar to how we do for the model observations.
* Structure vector store observation attributes in dedicated enums, including one for the Spring AI Kinds to avoid hard-coding the same value in a lot of places. This follows the OpenTelemetry Semantic Conventions as much as possible. Also, adopt Spring usual non-null-by-default strategy as much as possible.
* Align vector store conventions to the chat model ones, and follow alphabetical order for values. This is particularly useful for the convention classes, for which the Micrometer performance of exporting telemetry data improves when key values are added already sorted to the context.
* Fix flaky test in Mistral AI.
* Improve Qdrant integration tests.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
PgVectorFilterExpressionConverter was generating incorrect SQL for
IN and NOT IN filters with PostgreSQL JSON data types. This caused
BadSqlGrammarException errors when executing queries.
This change modifies the converter to generate correct SQL syntax
for these operations, ensuring compatibility with PostgreSQL's JSON
handling capabilities.
Why:
- Improves query reliability for PgVector stores
- Enables more complex filtering operations on JSON data
- Eliminates unexpected errors in query execution
Fixes#1179
Implementation:
- Introduce AbstractObservationVectorStore with instrumentation for add, delete, and similaritySearch methods
- Create VectorStoreObservationContext to capture operation details
- Implement DefaultVectorStoreObservationConvention for naming and tagging
- Add VectorStoreObservationDocumentation for defining observation keys
- Create VectorStoreObservationAutoConfiguration for auto-configuring observations
- Add VectorStoreObservationProperties to control optional observation content filters
- Update VectorStore interface with getName() method
- Modify PgVectorStore and SimpleVectorStore to extend AbstractObservationVectorStore
- Add vector_store Spring AI kind
Filters:
- Implement VectorStoreQueryResponseObservationFilter
- Add VectorStoreDeleteRequestContentObservationFilter and VectorStoreAddRequestContentObservationFilter
Enhancements:
- Update PgVectorStoreAutoConfiguration to support observations
- Add observation support to PgVectorStore's Builder
- Add VectorStoreObservationContext.Operation enum with ADD, DELETE, and QUERY options
Tests:
- Add tests for VectorStore context, convention, and filters
- Add VectorStoreObservationAutoConfiguration tests
- Add PgVectorObservationIT
Resolves#1205
This change allows users to specify custom names, facilitating management of multiple vector databases within a single database instance.
Key changes:
- Implement configurable schema, table, and index names for PgVectorStore
- Add properties to set custom schema and table names
- Introduce optional schema/table & field validation for custom configurations
- Include additional tests for new configurations and existing deployments
Additional improvements:
- Rename properties to schemaName, tableName, and schemaValidation
- Update pgvector documentation with new properties
- Add schema/table name tests to PgVectorStoreAutoConfigurationIT and PgVectorStorePropertiesTests
- Create standalone PgVectorSchemaValidator class for schema/table validation
- Add missing 'CREATE SCHEMA IF NOT EXISTS' when initializeSchema=true
- Remove redundant code and classes
Resolves#747
Co-authored-by: Christian Tzolov <ctzolov@vmware.com>
* Rename the ModelClient class hierarchy into Model:
- Rename ModelClient into Model. Update all code and doc references.
- Rename ChatClient to ChatModel. Update all ChatClient suffixes and chatClient fields and variables in code and doc.
- Rename EmbeddingClient into EmbeddingModel. Update the XxxEmbeddingClient class and variable suffixes and embeddingClient variables and fields in code and docs.
- Rename ImageClient into ImageModel.
- Rename SpeechClient into SpeechModel.
- Rename TranscriptionClient into TranscriptionModel.
- Update all javadocs and antora pages. Update the related diagrams.
* Create fluent API in ChatClient interface that now includes streaming support
* Add OpenAI FunctionCallbackWrapper2IT auto-config tests.
* Add ChatClientTest mockito testing.
* Add ChatModel#getDefaultOptions(), and remove @FunctionalInterface
* ChatModel enums extend the new ModelDescription interface.
* Implement fromOptions copy method in every ChatOptions implementation.
* Extend ChatClient to use the model default options if not provided explicitly.
* Update readme to provide guidance on how to adapt to breaking changes.
Co-authored-by: Christian Tzolov <ctzolov@vmware.com>
Co-authored-by: Mark Pollack <mpollack@vmware.com>
- Resolve an issue where a new index keeps getting created during application start up.
- Solution is is to create an index only if an index on the embedding column does not exist.
- Add missing index name.
Moved up one package level the following classes
* org.springframework.ai.huggingface.client.HuggingfaceChatClient
* org.springframework.ai.openai.client.OpenAiChatClient and org.springframework.ai.openai.embedding.OpenAiEmbeddingClient
* org.springframework.ai.vertex.generation.VertexAiChatClient and org.springframework.ai.vertex.embedding.VertexAiEmbeddingClient
Fixes#211
- Introducing a new OpenAiApi native client for OpenAI API and get rid of the theokanning library.
Amongst others the OpenAiApi allows:
- easy base-url configuration (e.g. TAS-AI)
- Flux response for streaming OpenAI results.
- Exposes the http headers containing important metadata
- Pure Spring ecosystem, making it easier for Graal VM
- Define a new AiStreamClient interface returning Flux<AiResponse>
- Refactor OpenAiClient and to use the new OpenAiApi and implement the AiStreamClient.
- Use spring-retry to improve the OpenAI EmbeddingClient stability on 503 error.
- Remove the OpenAI http header interceptor as the OpenAiApi returns ResponseEntity<T> that provides direct access to the headers.
- Refactor the metadata headers and usage extraction.
- Remove redundant and obsolete classes.
- Fix dependency issue with Pinecone, netty-codec-http2 and Spring Boot 3.2
- Add NOT expression type to the portable Filter.Expression model.
- Add NOT to the Antlr grammar and implement the related parser listener method to generate Filter NOT expressions.
- Add NOT support to the filter programming DSL.
- Implement FilterHelper.negation for logically transform any boolean expression with NOT statements into
semantically equivalent one with NOT applied to the leaf expressions.
- Add tests for paresers, converters and vectorsores ITs.
- Move the filter IN/NIN expansion logic to the FilterHelper
- Factor out the filter IN/NIN boolean expression expansion logic out of Weaviate up to the FilterHelper.
- add in/nin expantion FilterHelper tests
- Implement ChromaApi client, based on Chroma REST API.
- Implement ChromaVectorStore, including support for filter expression conversion.
- Common VectorStoreUtil class to share to/from Float/Double list/array convertion as well as Json/Map convertions.
- Add ITs including for Basic Auth and Token autheticatios.
- Add ChromaApi security support for BasicAuth and Token.
- Fix an issue with Text filter expression parser, related to double-quoted identifiers.
- Add Chroma README.md.
- Add Chroma boot autoconfiguration
Resolves# #86
- Collapses all VectorStore similiaritySearch methdos into one with SearchRequest builder.
- Fix all affected code and tests.
- Bump the project version to 0.7.1.
- Add tests
- Add autoconfigurations for milvus, pinecone and pgvecor stores.
- Improve and unify the VectorStore ITs.
- Make use of TrasformersEmbeddingClient for auto-configurations ITs.
* Clean up README.md files in Milvus, PGvector, and Pinecone modules.
* Apply consistent treatment of 'model' when used as an AI concept, e.g. AI model or Embedding model.
* Apply consistent treatment of 'vector store' and 'vector database' references.
* Simplify sentence structures.
Closes#79
- Extend the VectorStore with similaritySearch using metadata filters using internal DSL and external DSL using Antlr
- Metdata support for Pinecone, Milvus, and pgvector vector stores
- PGVectorStore uses explict ::jsonpath casting for the pgvector filter expression to avoid injections
- Add unit tests for the filter converters, parser and DSL.
- Add ITs for the 3 vector stores
Resolves: #75
