Does Dify make newly added source content findable?
Dify made newly added source content findable after the update path completed. The new document was created through the ingestion endpoint, indexing reached completed before retrieval, and the retrieval call returned that same document first; two additional segments also pointed to it.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
Document added to the source, then queried after a refreshPassEvidence
“When does the Tromso depot open?”
Depot bulletin - a new depot in the region For the service desk, the Bergen depot and central stores. What is opening The Tromso depot opens on 14 October 2026 and will hold four Tolvan C5 loan units and a full Brannoc spares kit. It is the third depot in the network and the first above the Arctic Circle.
Transcribed from Proof 2 · Screenshot
| ✓ | Expected: Newly added content should come back after the update path finishes; elapsed time is noted but not graded.Found: The new document was created, indexing completed before retrieval, and the retrieval call returned that same document first with the opening fact. |
POST /datasets/{ms_v0_dataset_id}/document/create-by-file Request: data = {"indexing_technique": "high_quality", "process_rule": {"mode": "automatic"}} file = B05_tromso_depot_bulletin.md (text/markdown) Status: 200 Response body: { "document": { "id": "3aae3128-23c3-488f-abc9-028130867f21", "position": 5, "data_source_type": "upload_file", "data_source_info": { "upload_file_id": "3e42654c-a8db-4ac4-b025-87f154172c8a" }, "name": "B05_tromso_depot_bulletin.md", "created_from": "api", "indexing_status": "waiting", "error": null, "enabled": true, "archived": false, "display_status": "queuing" }, "batch": "20260920201619131764" } Polled GET /datasets/{ms_v0_dataset_id}/documents until B05_tromso_depot_bulletin.md's indexing_status flipped to "completed" (error: null) -- confirming the add mutation (MS-v0 -> MS-v1) finished indexing before the query below was sent. Dataset document list after the mutation (5 documents, all completed): B01_oncall_rota_notes.md completed B02_shipping_lead_times.pdf completed B03_approved_supplier_list.docx completed B04_site_access_notes.txt completed B05_tromso_depot_bulletin.md completed -------------------------------------------------------------------------------- POST /datasets/{ms_v0_dataset_id}/retrieve Request body: { "query": "When does the Tromso depot open?" } Status: 200 Response body: { "query": { "content": "When does the Tromso depot open?" }, "records": [ { "segment": { "id": "c6e769d0-1847-475d-bfbd-8b645d64787f", "position": 1, "document_id": "3aae3128-23c3-488f-abc9-028130867f21", "content": "Depot bulletin - a new depot in the region\n\nFor the service desk, the Bergen depot and central stores.\n\nWhat is opening\n\nThe Tromso depot opens on 14 October 2026 and will hold four Tolvan C5 loan units and a full Brannoc spares kit. It is the third depot in the network and the first above the Arctic Circle.\n\nWhy", "sign_content": null, "answer": null, "word_count": 314, "tokens": 76, "keywords": [], "index_node_id": "c5003335-7b17-483a-8e4c-2f55fbd34bd4", "index_node_hash": "e824cd6d14b027c3eb0b79de76e41907195b3a621185e9b3d0c05535e7d22f24", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789935380, "indexing_at": 1789935382, "completed_at": 1789935384, "error": null, "stopped_at": null, "document": { "id": "3aae3128-23c3-488f-abc9-028130867f21", "data_source_type": "upload_file", "name": "B05_tromso_depot_bulletin.md", "doc_type": null, "doc_metadata": null } }, "child_chunks": [], "score": 0.77432114, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "eddadeb9-4458-4202-ae6b-c7f7bb739a99", "position": 2, "document_id": "3aae3128-23c3-488f-abc9-028130867f21", "content": "Why\n\nResponse to the northern fields has been limited by the sailing time from Bergen rather than by engineering. Holding loan stock and a spares kit locally removes the leg that has cost the most time on recent tickets.\n\nStaffing\n\nOne engineer and a shared stores controller, working 07:00 to 15:00 local time, Monday to Friday. Out of hours the northern sites continue to page the existing duty engineer rota; the new depot does not change how a fault is reported.\n\nWhat to do differently", "sign_content": null, "answer": null, "word_count": 490, "tokens": 103, "keywords": [], "index_node_id": "d1fa971d-5601-4b8b-89be-7836eb3145fa", "index_node_hash": "7ba0c6213f4ab87766e196a7788505072d642ec000eafa1d3094f4d4ef503765", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789935380, "indexing_at": 1789935382, "completed_at": 1789935385, "error": null, "stopped_at": null, "document": { "id": "3aae3128-23c3-488f-abc9-028130867f21", "data_source_type": "upload_file", "name": "B05_tromso_depot_bulletin.md", "doc_type": null, "doc_metadata": null } }, "child_chunks": [], "score": 0.50368106, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "923d96e7-4ea2-431f-b4e4-562657733736", "position": 3, "document_id": "3aae3128-23c3-488f-abc9-028130867f21", "content": "What to do differently\n\nStop routing northern loan requests through Bergen once the depot opens. Ring the new depot directly. Bergen keeps its own loan pool and its own spares kit, and nothing moves out of Bergen to stock the new site.\n\nWhat is not changing\n\nCalibration stays in the laboratory. The new depot does not calibrate, does not break a calibration seal, and does not open a pressure housing.", "sign_content": null, "answer": null, "word_count": 402, "tokens": 83, "keywords": [], "index_node_id": "8d355721-5320-48b0-8611-ca42a4c41be5", "index_node_hash": "060ac7a4b367db9e1d91b05dd74ebb9179fda7593e7e4ca001f6c135833108df", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789935380, "indexing_at": 1789935382, "completed_at": 1789935384, "error": null, "stopped_at": null, "document": { "id": "3aae3128-23c3-488f-abc9-028130867f21", "data_source_type": "upload_file", "name": "B05_tromso_depot_bulletin.md", "doc_type": null, "doc_metadata": null } }, "child_chunks": [], "score": 0.50290453, "tsne_position": null, "files": [], "summary": null }, { "segment": { "id": "24590d8c-a4c3-4b53-a71d-1e76e83a7503", "position": 2, "document_id": "f2014483-7c26-430c-a9f2-b533ff43b0bb", "content": "Road and ferry 4 working days\r\nGothenburg Road and ferry, groupage 7 working days\r\nEsbjerg Road and ferry, groupage 9 working days\r\nBergen Road and ferry, groupage 11 working days\r\nLead times to the Nordic depots assume a groupage service.", "sign_content": null, "answer": null, "word_count": 239, "tokens": 64, "keywords": [], "index_node_id": "661cf69a-097b-4964-ba5a-03e87d703bc8", "index_node_hash": "507133254e1e6366fe004cf040ddcce992d61348e757aa0dae8f23b0f4e7d3b2", "hit_count": 0, "enabled": true, "disabled_at": null, "disabled_by": null, "status": "completed", "created_by": "f1034bbd-04df-4592-ba22-56dac49ae8ad", "created_at": 1789754430, "indexing_at": 1789754431, "completed_at": 1789754433, "error": null, "stopped_at": null, "document": { "id": "f2014483-7c26-430c-a9f2-b533ff43b0bb", "data_source_type": "upload_file", "name": "B02_shipping_lead_times.pdf", "doc_type": null, "doc_metadata": null } }, "child_chunks": [], "score": 0.4775899, "tsne_position": null, "files": [], "summary": null } ] }
The product had to make newly added content findable once indexing finished. The document was created, indexing completed before the query, and retrieval returned that document first with the opening fact, so the case passes.
Extra matching segments. The added document also supplied two more strong matches, and the best other document scored lower.
API surface confirmed. The upload response said it came from the API, matching the request path.
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Managed RAG → | 15 scenarios · 9 tools |
| Capability | Knowledge Sync → | |
| Scenario | New content is added to the source → | |
| Tool | Dify → |
Global scenario definition → · Global capability definition → · Dify product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.