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
| Feature | Status | Notes |
|---|---|---|
| Plain-text documents through the REST API | Available | Documents are submitted as JSON with a contents string |
| Asynchronous processing with status tracking | Available | The document status reports pending, success or failed |
| Document versions and updates by external identifier | Available | Previous versions are expired by default and remain readable |
| Point-in-time reads | Available | Returns a document, or the fragments of a document, as they existed at a specified time |
| Expiry and deletion | Available | Single documents, a whole pipeline, or all pipelines |
| Metadata with an optional JSON Schema | Available | Validated on ingestion |
| Text splitters | Available | Character, recursive character, code, Markdown header and token splitters. The token splitter needs internet access. The recursive JSON splitter cannot be created in the current release, and the NLTK sentence splitter needs a package that the standard images do not include |
| Five embedding providers | Available | FastEmbed, OpenAI-compatible endpoints, GPT4All, Hugging Face sentence-transformers and Hugging Face inference endpoints |
| File upload and parsing (PDF, Office, HTML, audio) | Planned | Text must be extracted before submission |
Search and retrieval
| Feature | Status | Notes |
|---|---|---|
| Vector similarity search | Available | Cosine (default), Euclidean or dot product distance |
| Maximal marginal relevance (MMR) search | Available | Balances relevance against variety |
| Full-text search | Available | New in September 2026. Enabled per pipeline at creation. Language detected automatically across 17 languages |
| Metadata filters | Available | Comparisons, ranges, pattern matching, set membership and boolean logic |
| Taxonomy-aware filters | Available | Match a value and every value beneath that value in a hierarchy |
| Custom metadata indexes | Partial | Indexes can be created on declared metadata fields, but metadata filters do not use them in the current release |
| Classification scoping | Available | Hierarchical or exact matching on every search |
| Hybrid search (vector plus full-text) | Partial | The client application runs a vector search and a full-text search and fuses the results. See the guide Combine full-text and vector results |
| Native hybrid search with BM25 re-ranking | Planned | One request that runs both searches and re-ranks the combined results inside Foundation4 |
Generation
| Feature | Status | Notes |
|---|---|---|
| Registered LLMs | Available | Any OpenAI-compatible model that the deployment can reach |
| Agents with prompt templates and retrieval placeholders | Available | Similarity and MMR placeholders |
| Streaming responses | Available | NDJSON, server-sent events or plain text |
| Execution tracing | Available | Records the prompt and fragments behind a response for 60 minutes |
| OpenAI-compatible chat completions endpoint | Partial | Relays requests to a registered LLM so that OpenAI SDKs can call registered models. The endpoint does not add retrieval |
| Full-text and hybrid placeholders in agents | Planned | Agents use similarity and MMR retrieval |
| Conversation history in agents | Planned | Agents are stateless; the client application supplies any history |
Agents and direct LLM queries call the model through the OpenAI Responses API and require an API key on the registered LLM. The chat completions endpoint uses the Chat Completions API. Most commercial providers support both APIs. Some self-hosted model servers implement only the Chat Completions API; those servers work with the chat completions endpoint but not with agents. Support for agents on any OpenAI-compatible server, with or without an API key, is planned.
Integration and access
| Feature | Status | Notes |
|---|---|---|
| REST API with OpenAPI description | Available | Served by every deployment at /openapi.json, with interactive documentation at /docs |
| API keys with read, write and execute permissions | Available | Per object type or per object, with expiry and deactivation |
| MCP endpoint | Partial | Streamable HTTP with three read-only tools: list pipelines, list the classifications of a pipeline, and search. No filters, ingestion or agent tools; reachable only through a port forward |
| Expanded MCP tools | Planned | |
| Administrative dashboard | Partial | Browse objects, add documents, run searches, test embedding models and LLMs. Pipelines, agents and API keys are created through the API |
Operations
| Feature | Status | Notes |
|---|---|---|
| Kubernetes installation with Helm | Available | Two charts: shared services and the application |
| Air-gapped deployment | Available | Model 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 metrics | Available | From the API server and the workers |
| OpenTelemetry tracing and request identifiers | Available | |
| Licensing | Available | License limits apply per deployment |