diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/overview.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/ai-accelerator-overview.mdx similarity index 93% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/overview.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/ai-accelerator-overview.mdx index f3a00b7dedb..ddf2c650783 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/overview.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/ai-accelerator-overview.mdx @@ -1,18 +1,18 @@ --- title: "EDB Postgres AI - AI Accelerator - Overview" -navTitle: "Overview" +navTitle: "AI Accelerator Overview" description: "Overview of the EDB Postgres AI AI Accelerator suite of tools including EDB PGvector and Pipelines." --- ## What is the AI Accelerator? -AI Accelerator simplifies AI data management by combining vector search from open source pgvector with Pipelines, an extension for AI data pipeline automation. It handles vector embedding operations for structured and unstructured data, simplifying similarity searches and natural language querying, and streamlines development of AI-powered applications by providing retrieval of AI-ready data in a familiar Postgres environment. +AI Accelerator simplifies AI data management by combining vector search from open source PGvector with Pipelines, an extension for AI data pipeline automation. It handles vector embedding operations for structured and unstructured data, simplifying similarity searches and natural language querying, and streamlines development of AI-powered applications by providing retrieval of AI-ready data in a familiar Postgres environment. ## Features ### Vector Toolkit -The EDB Pipelines extension enables automated vector embedding, storage, and retrieval workflows, and it comes preloaded with pgvector for seamless management of vector data in Postgres. This enables developers to build complex GenAI functionality using SQL commands in the familiar Postgres environment — with just 5 lines of code instead of 130+. +The EDB Pipelines extension enables automated vector embedding, storage, and retrieval workflows, and it comes preloaded with PGvector for seamless management of vector data in Postgres. This enables developers to build complex GenAI functionality using SQL commands in the familiar Postgres environment — with just 5 lines of code instead of 130+. ### Swappable Configurations diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/gettingstarted/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/gettingstarted/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/gettingstarted/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/gettingstarted/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/images/aidb-overview-withbackground.png b/advocacy_docs/edb-postgres-ai/ai-accelerator/images/aidb-overview-withbackground.png similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/images/aidb-overview-withbackground.png rename to advocacy_docs/edb-postgres-ai/ai-accelerator/images/aidb-overview-withbackground.png diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/index.mdx index 0710609c137..df6c1228160 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/index.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/index.mdx @@ -5,10 +5,22 @@ directoryDefaults: product: "EDB Postgres AI" iconName: BrainCircuit indexCards: simple -description: "All about the EDB Postgres AI - AI Accelerator suite of tools including Pipelines and pgvector." +description: "All about the EDB Postgres AI - AI Accelerator suite of tools including Pipelines and PGvector." navigation: -- overview -- pipelines +- ai-accelerator-overview +- "#Pipelines" +- pipelines-overview +- installing +- gettingstarted +- "#Components" +- models +- retrievers +- pgfs +- "#Resources" +- reference +- rel_notes +- licenses +- pgvector redirects: - /edb-postgres-ai/ai-ml/ --- diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/complete.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/installing/complete.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/complete.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/installing/complete.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/installing/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/installing/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/packages.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/installing/packages.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/installing/packages.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/installing/packages.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/licenses.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/licenses.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/licenses.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/licenses.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/primitives.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/primitives.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/primitives.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/primitives.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/bert.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/bert.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/bert.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/bert.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/clip.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/clip.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/clip.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/clip.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/openai-completions.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/openai-completions.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/openai-completions.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/openai-completions.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/openai-embeddings.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/openai-embeddings.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/openai-embeddings.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/openai-embeddings.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/t5.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/t5.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/models/supported-models/t5.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/t5.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/index.mdx similarity index 94% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/index.mdx index aa99441b7bc..908ef5d5a4b 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/index.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/index.mdx @@ -8,7 +8,7 @@ Pipelines has a "Postgres File System" (PGFS) that allows you access external st PGFS is a key component of Pipelines, allowing you to work with data which is not stored in the database, either because it is too large or because it is not structured in a way that is suitable for a relational database. -pgfs is implemented as a foreign data wrapper (FDW) and is installed as an extension. The extension provides a set of functions to interact with the file system from within the database. +PGFS is implemented as a foreign data wrapper (FDW) and is installed as an extension. The extension provides a set of functions to interact with the file system from within the database. ## Installing the PGFS extension diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/local.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/local.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/local.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/local.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/s3.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/s3.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgfs/s3.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/pgfs/s3.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgvector/index.mdx similarity index 81% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/pgvector/index.mdx index 12542892caa..34fcb228ad5 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/pgvector/index.mdx @@ -1,21 +1,21 @@ --- -title: "AI Accelerator - PGVector" -navTitle: "PGVector" -description: "PGVector is a Postgres extension that provides vector data types and functions to store and manipulate vector data." +title: "AI Accelerator - PGvector" +navTitle: "PGvector" +description: "PGvector is a Postgres extension that provides vector data types and functions to store and manipulate vector data." deepToC: true --- -## What is PGVector +## What is PGvector PGvector is an extension for Postgres that enables efficient storage and similarity search of high-dimensional vector data, commonly used for machine learning models, recommendation systems, and natural language processing applications. ### Part of the EDB Postgres AI platform -EDB Postgres AI with pgvector delivers a flexible solution for enterprise AI, integrating seamlessly with existing Postgres environments. It outperforms standalone vector databases with 4.22X faster queries and eliminates data silos via integrations with 18X cost-efficient object storage. This unified platform accelerates AI deployment, simplifies management, and ensures up to 99.999% availability, enabling businesses to innovate rapidly and future-proof their data infrastructure without disrupting current operations. +EDB Postgres AI with PGvector delivers a flexible solution for enterprise AI, integrating seamlessly with existing Postgres environments. It outperforms standalone vector databases with 4.22X faster queries and eliminates data silos via integrations with 18X cost-efficient object storage. This unified platform accelerates AI deployment, simplifies management, and ensures up to 99.999% availability, enabling businesses to innovate rapidly and future-proof their data infrastructure without disrupting current operations. ### Native Vector Data Type Support -pgvector on EDB Postgres AI enables storage of AI/ML model embeddings as first-class data types, allowing efficient indexing and querying of large volumes of AI data stored in object storage, seamlessly integrated with traditional relational data. +PGvector on EDB Postgres AI enables storage of AI/ML model embeddings as first-class data types, allowing efficient indexing and querying of large volumes of AI data stored in object storage, seamlessly integrated with traditional relational data. ### Advanced 4.22X Vector Query @@ -23,11 +23,11 @@ Extends standard SQL with vector-specific operators and functions, enabling comp ### High-performance Indexing -With real-time indexing, storage, and querying of AI data, pgvector enables efficient vector similarity search on embeddings from various LLMs, while leveraging Postgres transactionality for consistent handling of mixed workloads. +With real-time indexing, storage, and querying of AI data, PGvector enables efficient vector similarity search on embeddings from various LLMs, while leveraging Postgres transactionality for consistent handling of mixed workloads. ### Integrated Vector Data Platform -pgvector unifies vector database capabilities with EDB Postgres AI's mature enterprise features, ensuring high availability, robust backup/recovery, strong security, and ACID data integrity, all within a single vendor solution for comprehensive data management and AI workloads. +PGvector unifies vector database capabilities with EDB Postgres AI's mature enterprise features, ensuring high availability, robust backup/recovery, strong security, and ACID data integrity, all within a single vendor solution for comprehensive data management and AI workloads. ## Installation @@ -35,4 +35,4 @@ The extension is included with AI Accelerator's Pipelines and installed automati ## Further information -For more information on the pgvector extension, see the [pgvector repository](https://github.com/pgvector/pgvector). +For more information on the PGvector extension, see the [pgvector repository](https://github.com/pgvector/pgvector). diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/overview.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines-overview.mdx similarity index 98% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/overview.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines-overview.mdx index 289c80dfec1..7c0732c4cd0 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/overview.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines-overview.mdx @@ -5,7 +5,7 @@ description: "Where to start with AI Accelerator Pipelines." prevNext: True --- -As part of the EDB Postgres AI's AI Accelerator Pipelines abstracts away the complexity of working with AI data. It transforms Postgres into a powerful platform for AI data management, combining vector search from pgvector with automation for complex AI workflows. +As part of the EDB Postgres AI's AI Accelerator Pipelines abstracts away the complexity of working with AI data. It transforms Postgres into a powerful platform for AI data management, combining vector search from PGvector with automation for complex AI workflows. ## Pipelines, Auto Embedding, and Intelligent Retriever diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/index.mdx deleted file mode 100644 index fd0beaa2ecb..00000000000 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/index.mdx +++ /dev/null @@ -1,23 +0,0 @@ ---- -title: "AI Accelerator - Pipelines" -navTitle: "Pipelines" -indexCards: simple -iconName: BrainCircuit -description: "Installing and using AI Accelerator Pipelines with the aidb and pgfs extensions." -navigation: -- "#Introducing" -- overview -- installing -- gettingstarted -- "#Components" -- models -- retrievers -- pgvector -- pgfs -- "#Resources" -- reference -- rel_notes -- licenses ---- - -As part of the EDB Postgres AI platform, Pipelines abstracts away the complexity of working with AI data. It transforms Postgres into a powerful platform for AI data management, combining vector search from pgvector with automation for complex AI workflows. diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/reference/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/reference/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/models.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/reference/models.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/models.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/reference/models.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/pgfs.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/reference/pgfs.mdx similarity index 98% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/pgfs.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/reference/pgfs.mdx index 0e0051d77ec..04282bf4d50 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/pgfs.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/reference/pgfs.mdx @@ -5,7 +5,7 @@ description: "Reference documentation for EDB Postgres AI - AI Accelerator - Pip deepToC: true --- -This section provides reference documentation for EDB Postgres AI AI Accelerator Pipelines PGFS. It includes information on the functions and views available in the [pgfs](../pgfs) extension that gives aidb access to S3-compatible file systems and local file systems. +This section provides reference documentation for EDB Postgres AI AI Accelerator Pipelines PGFS. It includes information on the functions and views available in the [PGFS](../pgfs) extension that gives aidb access to S3-compatible file systems and local file systems. ## Functions diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/retrievers.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/reference/retrievers.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/reference/retrievers.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/reference/retrievers.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx similarity index 97% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx index bb95fd6876f..f733286f562 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/ai-accelerator_1.0.0_rel_notes.mdx @@ -16,7 +16,7 @@ This is the GA release of EDB Postgres AI - AI Accelerator - Pipelines. Since th - Support for external models with OpenAI API. - Secure management of API credentials vie postgres "user mapping" feature. - Model registry that allows configuring internal/external models. -- pgfs/volumes allows working with external data from S3 object stores and file systems. +- PGFS/volumes allows working with external data from S3 object stores and file systems. - Low-level primitives for models: encode, transform for image and text data. - Enhanced retriever concept for data retrieval. - Support image and text data, including: Postgres tables, external storage, and ad-hoc queries. diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/src/meta.yml b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/meta.yml similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/src/meta.yml rename to advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/meta.yml diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/src/rel_notes_1.0.0.yml b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/rel_notes_1.0.0.yml similarity index 96% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/src/rel_notes_1.0.0.yml rename to advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/rel_notes_1.0.0.yml index d58424df9e0..23f6efe37ab 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/rel_notes/src/rel_notes_1.0.0.yml +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/rel_notes_1.0.0.yml @@ -8,7 +8,7 @@ highlights: | - Support for external models with OpenAI API. - Secure management of API credentials vie postgres "user mapping" feature. - Model registry that allows configuring internal/external models. - - pgfs/volumes allows working with external data from S3 object stores and file systems. + - PGFS/volumes allows working with external data from S3 object stores and file systems. - Low-level primitives for models: encode, transform for image and text data. - Enhanced retriever concept for data retrieval. - Support image and text data, including: Postgres tables, external storage, and ad-hoc queries. @@ -44,7 +44,7 @@ relnotes: type: Enhancement severity: High impact: High -- relnote: pgfs/volumes allows working with external data from S3 object stores and file systems +- relnote: PGFS/volumes allows working with external data from S3 object stores and file systems details: | The tech preview could only work with S3 in retrievers. Now, the volume concept allows working with external data in general. jira: AID-77 diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/concepts.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/concepts.mdx similarity index 98% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/concepts.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/concepts.mdx index 3182a27a286..d1875427fe2 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/concepts.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/concepts.mdx @@ -32,7 +32,7 @@ You can combine any data source with any data type: Retrievers always need a "vector table" to store the vector embeddings that belong to the source data. We use a model with "encoder" capabilities to generate the vectors for the source data. -Each model has a different "dimensionality" i.e. number of dimensions of the vector (the vector [1, 2, 2] has 3 dimensions). We use pgvector "vector" column types to store the embeddings. And those have a fixed number of dimensions. For this reason, the encoder interface on the models returns how many dimensions the vectors will have. +Each model has a different "dimensionality" i.e. number of dimensions of the vector (the vector [1, 2, 2] has 3 dimensions). We use PGvector "vector" column types to store the embeddings. And those have a fixed number of dimensions. For this reason, the encoder interface on the models returns how many dimensions the vectors will have. We create the vector table, or support using an existing one. The vector column dimensionality must fit the model. diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/example.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/example.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/example.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/example.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/index.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/index.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/index.mdx diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/usage.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/usage.mdx similarity index 100% rename from advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/retrievers/usage.mdx rename to advocacy_docs/edb-postgres-ai/ai-accelerator/retrievers/usage.mdx