Skip to main content

Feature status

This page lists the capabilities of Foundation4 by status. The page is updated with each release and replaces the former Roadmap page. Available means the capability is reachable through the public API. Partial means the capability works within the limits stated in the notes. Planned means the capability is on the roadmap and not yet available.

Content and ingestion​

FeatureStatusNotes
Plain-text documents through the REST APIAvailableDocuments are submitted as JSON with a contents string
Asynchronous processing with status trackingAvailableThe document status reports pending, success, failed or canceled. A failed document records the reason after 12 attempts
Document versions and updates by external identifierAvailablePrevious versions are expired by default and remain readable
Point-in-time readsAvailableReturns a document, or the fragments of a document, as they existed at a specified time
Expiry and deletionAvailableSingle documents, a whole pipeline, or all pipelines
Metadata with an optional JSON SchemaAvailableValidated on ingestion
Text splittersAvailableCharacter, recursive character, code, Markdown header, token, NLTK, spaCy and sentence-transformers token splitters. The token splitter reads its encoding files from a model image or downloads them. The spaCy and sentence-transformers token splitters need their package images. The recursive JSON splitter cannot be created in the current release
Five embedding providersAvailableFastEmbed, OpenAI-compatible endpoints, GPT4All, Hugging Face sentence-transformers and Hugging Face inference endpoints
File upload and parsing (PDF, Office, HTML, audio)PlannedText must be extracted before submission

Search and retrieval​

FeatureStatusNotes
Search indexesAvailableVector, full-text and BM25 indexes per pipeline, added, rebuilt, switched or removed while the pipeline holds documents. Several embedding models per pipeline
Vector similarity searchAvailableCosine distance by default. Euclidean and dot product distance after adding a distance index
Maximal marginal relevance (MMR) searchAvailableBalances relevance against variety
Full-text searchAvailableFull-text index with PostgreSQL text search, language detected automatically across 36 languages, or BM25 index with a configurable tokenizer. Hugging Face tokenizers need internet access when the index is created
Document pathsAvailableSearches, agents and document lists scoped to a path pattern. A search without a path covers only documents without a path. Paths restrict no access
History searchAvailableThe most recent fragments of a pipeline, newest first
Metadata filtersAvailableComparisons, ranges, pattern matching, set membership and boolean logic, on top-level and nested fields
Taxonomy-aware filtersAvailableMatch a value and every value beneath that value in a hierarchy
Custom metadata indexesAvailableIndexes on declared top-level metadata fields, built on the expression that metadata filters use. PostgreSQL decides for each query whether to use an index
Classification scopingAvailableHierarchical or exact matching on every search, within the classification allow-list of the API key
Hybrid searchAvailableOne request that searches several indexes and fuses the results by reciprocal rank fusion, with equal weights and no threshold. See the guide Set up hybrid search

Generation​

FeatureStatusNotes
Registered LLMsAvailableAny OpenAI-compatible model that the deployment can reach
Agents with prompt templates and retrieval placeholdersAvailableSimilarity, MMR, full-text, hybrid and history placeholders on the pipeline's default search indexes
Streaming responsesAvailableNDJSON, server-sent events or plain text
Execution tracingAvailableRecords the prompt and fragments behind a response for 60 minutes
OpenAI-compatible chat completions endpointPartialRelays requests to a registered LLM so that OpenAI SDKs can call registered models. The endpoint does not add retrieval
Conversation history in agentsPlannedAgents are stateless; the client application supplies any history

Agents, direct LLM queries and the chat completions endpoint call the chat completions API of the model server, so a model server that implements that API serves every feature. The API key of a registered LLM is optional.

Integration and access​

FeatureStatusNotes
REST API with OpenAPI descriptionAvailableServed by every deployment at /openapi.json, with interactive documentation at /docs
API keys with read, write and execute permissionsAvailablePer object type or per object, with expiry and deactivation
MCP serverAvailableStreamable HTTP with 18 tools for pipelines, every search type, documents, taxonomies and agents, one prompt per agent and documents as resources. API key headers only, no OAuth authorization. Pipelines, agents and keys are created through the REST API
Administrative dashboardPartialBrowse objects, add documents, run searches, test embedding models and LLMs. Pipelines, agents and API keys are created through the API

Operations​

FeatureStatusNotes
Kubernetes installation with HelmAvailableTwo charts: shared services and the application
Air-gapped deploymentAvailableModel weights and packages ship as container images. The built-in FastEmbed models that are not in the API server image and the token splitter need internet access. The Models, packages and air-gapped installs page lists what works offline and provides the checklist
Prometheus metricsAvailableFrom the API server and the workers
OpenTelemetry tracing and request identifiersAvailable
LicensingAvailableLicense limits apply per deployment