canonical: https://jentic.com/apis/eyelevel.ai/eyelevel # EyeLevel GroundX API The EyeLevel GroundX API ingests documents and runs semantic search over them for retrieval-augmented generation. It takes local and remote documents, crawls websites, and organizes content into buckets that can be combined into groups for a single search. It tracks ingestion processing status, retries failed stages, and exposes a parsed X-Ray and extracted content per document, so an agent can build and query a knowledge base. ## For AI agents Ingest local, remote, and crawled documents into buckets, then run semantic search over them for retrieval. Track ingestion status and read parsed document content. Authenticated with an X-API-Key header. ## Scope Does not handle model training, chat completion, or payment. Use for ingesting documents and running semantic search for retrieval only. ## Capabilities - Ingest local and remote documents into a searchable bucket - Crawl a website and ingest its pages for retrieval - Run semantic search over ingested content and over documents - Organize content into buckets and combine buckets into groups - Track ingestion processing status and retry a failed stage - Inspect a document's parsed X-Ray and its extracted content ## Use cases ### RAG Knowledge Base Ingestion A team builds a retrieval knowledge base from mixed sources. The EyeLevel GroundX API ingests local uploads and remote documents, crawls a website for its pages, and stores everything in buckets, tracking processing status so an agent can wait for ingestion to finish and retry any failed stage before querying. Example prompt: Ingest a remote document into a bucket, poll its processing status until complete, then confirm the document appears in the bucket ### Semantic Search for Retrieval An assistant answers questions from a private corpus. The EyeLevel GroundX API runs semantic search over a bucket's content and across documents, returning relevant passages with their source so a model can ground its answer, and groups let one query span several buckets at once. Example prompt: Run a content search over a bucket for a user's question and return the top passages with their source documents ### AI Agent Retrieval via Jentic An AI agent grounds its answers through Jentic without holding the GroundX key itself. It searches by intent, receives the matching operation and its input schema, and runs ingestion and retrieval with the credential injected at run time, so a retrieval step slots into a larger agent workflow. Example prompt: Search Jentic for 'search my ingested documents', load the search operation schema, and run a query with Jentic-managed credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/ingest/documents/local` | Ingest local documents | | POST | `/v1/ingest/documents/remote` | Ingest remote documents | | POST | `/v1/search/documents` | Search across documents | | POST | `/v1/search/{id}` | Search content within a bucket or group | | GET | `/v1/ingest/{processId}` | Get ingestion processing status | | POST | `/v1/bucket` | Create a bucket | | GET | `/v1/ingest/document/{documentId}` | Get an ingested document | ## Key resources - **Ingestion** — Ingest and crawl documents via `/v1/ingest/documents/local`, `/v1/ingest/documents/remote`, and `/v1/ingest/documents/website` - **Search** — Run semantic search via `/v1/search/{id}` and `/v1/search/documents` - **Buckets and Groups** — Organize content via `/v1/bucket` and `/v1/group` ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 60 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 75 / 100 - Developer Experience & Jentic Compatibility: 61 / 100 - AI-Readiness & Agent Experience: 44 / 100 - Agent Usability: 93 / 100 - Security: 50 / 100 - AI Discoverability: 63 / 100 - **View full report:** https://jentic.com/apis/eyelevel.ai/eyelevel/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the EyeLevel GroundX API by hand means carrying its X-API-Key header, sequencing ingestion across local, remote, and crawl sources, and polling processing status yourself. Through Jentic you install once, import GroundX from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** GroundX puts the bucket, group, and document ids in the URL path, so a rule can pin your agent to one bucket and the operations you pick, such as ingest and search. You choose which operations it may call, so bucket deletion and API-key management are not included unless you add them. - **Credential handling:** Your GroundX key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'ingest a document' or 'search my documents', and Jentic returns the matching GroundX operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Pinecone Database API** — Managed vector database for storing and querying embeddings - **OpenAI API** — Generate the answer from the passages GroundX retrieves - **Cohere API** — Embeddings and reranking that can refine retrieval results ## FAQ ### What authentication does the EyeLevel GroundX API use? The EyeLevel GroundX API authenticates with an API key sent in the X-API-Key header per its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent. ### Can I crawl a website into a searchable index with the EyeLevel GroundX API? Yes. The crawl-website ingestion operation pulls a site's pages into a bucket, alongside local and remote document ingestion. You can track the processing status of each ingestion and retry a failed stage, then search the bucket once ingestion completes. ### What are the rate limits for the EyeLevel GroundX API? The OpenAPI spec does not specify rate limits for the EyeLevel GroundX API. Check the EyeLevel developer documentation for current limits, and use the customer usage operation to read your account's consumption by metric over a time range. ### How do I search my documents with the EyeLevel GroundX API through Jentic? Search Jentic for 'search my ingested documents' and it returns the GroundX search operation with its input schema. Load the schema, pass the bucket and query, and the key is injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Can I limit what my agent is allowed to do with the EyeLevel GroundX API? Yes. GroundX puts the bucket, group, and document ids in the URL path, so a rule can pin your agent to one bucket and the operations you pick. Allow ingestion and search while leaving bucket deletion, API-key management, and workflow changes out unless you add them. ### Is there an EyeLevel GroundX API MCP server? You don't need an MCP server to give your agent the EyeLevel GroundX API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the ingestion and search operations it needs without a separate server to install.