diff --git a/.gitea/workflows/refresh.yml b/.gitea/workflows/refresh.yml
index 22d9cf6..6ca226a 100644
--- a/.gitea/workflows/refresh.yml
+++ b/.gitea/workflows/refresh.yml
@@ -37,13 +37,13 @@ env:
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436,http://192.168.0.125:11434,http://192.168.0.126:11434
EMBED_MODEL: nomic-embed-text
- # Vision OCR of image-only pages (support/lifecycle matrices etc. — see
- # scrape/vision.py). Uses the host's primary Ollama on :11434, the only one
- # with a vision model; the embed pool above is nomic-only. qwen2.5vl:7b
- # scored best on the release-schedule matrix (55-56/56, ~18s, GPU-resident,
- # prompt-robust). Content-hash cached in corpus/.vision-cache/; VISION_MAX_NEW
- # bounds NEW OCRs per run so the cache fills incrementally instead of a
- # multi-hour first pass. Any failure degrades to the pre-vision behavior.
+ # Vision OCR of image-only data pages (the release-schedule matrix — see
+ # scrape/vision.py). OCR is a per-bundle opt-in (BundleSpec.ocr), so this
+ # only runs on allowlisted docs, NOT every screenshot in the corpus. Uses
+ # the host's primary Ollama on :11434, the only one with a vision model
+ # (the embed pool above is nomic-only). qwen2.5vl:7b scored best on the
+ # matrix (55-56/56, ~18s, GPU-resident). Any failure degrades to the
+ # pre-vision behavior.
VISION_OCR: "1"
VISION_URL: http://192.168.0.2:11434
VISION_MODEL: qwen2.5vl:7b
diff --git a/bundles.json b/bundles.json
index 3c8d98b..d41bb3e 100644
--- a/bundles.json
+++ b/bundles.json
@@ -14,7 +14,8 @@
"Published": "February 2026"
},
"landing_page": "GUID-709AAADB-A9C1-40B6-AD22-958EE7E6F312",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007510en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007510en_us",
+ "ocr": false
},
{
"slug": "morpheus_user_manual_8_1_1",
@@ -31,7 +32,8 @@
"Published": "March 2026"
},
"landing_page": "GUID-709AAADB-A9C1-40B6-AD22-958EE7E6F312",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007621en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007621en_us",
+ "ocr": false
},
{
"slug": "morpheus_user_manual_8_1_2",
@@ -48,7 +50,8 @@
"Published": "April 2026"
},
"landing_page": "GUID-709AAADB-A9C1-40B6-AD22-958EE7E6F312",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007732en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007732en_us",
+ "ocr": false
},
{
"slug": "morpheus_release_notes_8_1_0",
@@ -65,7 +68,8 @@
"Published": "February 2026"
},
"landing_page": "sd00007496en_us",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007496en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007496en_us",
+ "ocr": false
},
{
"slug": "morpheus_release_notes_8_1_1",
@@ -82,7 +86,8 @@
"Published": "March 2026"
},
"landing_page": "sd00007610en_us",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007610en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007610en_us",
+ "ocr": false
},
{
"slug": "morpheus_release_notes_8_1_2",
@@ -99,7 +104,8 @@
"Published": "April 2026"
},
"landing_page": "sd00007733en_us",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007733en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007733en_us",
+ "ocr": false
},
{
"slug": "morpheus_user_manual_9_0_0",
@@ -116,7 +122,8 @@
"Published": "May 2026"
},
"landing_page": "GUID-709AAADB-A9C1-40B6-AD22-958EE7E6F312",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00008014en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00008014en_us",
+ "ocr": false
},
{
"slug": "morpheus_release_notes_9_0_0",
@@ -133,7 +140,8 @@
"Published": "May 2026"
},
"landing_page": "sd00008017en_us",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00008017en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00008017en_us",
+ "ocr": false
},
{
"slug": "morpheus_quickspecs",
@@ -148,7 +156,8 @@
"abstract": "",
"dates": {},
"landing_page": "a50009231enw",
- "source_url": "https://www.hpe.com/psnow/doc/a50009231enw"
+ "source_url": "https://www.hpe.com/psnow/doc/a50009231enw",
+ "ocr": false
},
{
"slug": "morpheus_release_schedule",
@@ -165,6 +174,7 @@
"Published": ""
},
"landing_page": "sf000111242en_us",
- "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sf000111242en_us"
+ "source_url": "https://support.hpe.com/hpesc/public/docDisplay?docId=sf000111242en_us",
+ "ocr": true
}
]
diff --git a/corpus/.vision-cache/004727d68243b46f1c9da3b721ff2fd5c25c8522ddd32779ce764a89eb6d14a3.json b/corpus/.vision-cache/004727d68243b46f1c9da3b721ff2fd5c25c8522ddd32779ce764a89eb6d14a3.json
deleted file mode 100644
index 7da3c34..0000000
--- a/corpus/.vision-cache/004727d68243b46f1c9da3b721ff2fd5c25c8522ddd32779ce764a89eb6d14a3.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "004727d68243b46f1c9da3b721ff2fd5c25c8522ddd32779ce764a89eb6d14a3",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-37BE6AA0-10E5-4D0D-BCC1-0834A578B1EC-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Appliance Node | Description |\n|-----------------|-------------|\n| NGINX | Web server and reverse proxy |\n| MySQL | Relational database management system |\n| RabbitMQ | Message broker for distributed computing systems |\n| Elastic | Search engine and analytics platform |\n\nSingle Node Configuration:"
-}
diff --git a/corpus/.vision-cache/0819a450fc742f430aa7772e4ca095e0a756c6f626caaa6fdef38ddfe20c8bdd.json b/corpus/.vision-cache/0819a450fc742f430aa7772e4ca095e0a756c6f626caaa6fdef38ddfe20c8bdd.json
deleted file mode 100644
index ee95e3d..0000000
--- a/corpus/.vision-cache/0819a450fc742f430aa7772e4ca095e0a756c6f626caaa6fdef38ddfe20c8bdd.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "0819a450fc742f430aa7772e4ca095e0a756c6f626caaa6fdef38ddfe20c8bdd",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-444E2530-12E2-439A-A1C7-EED4D7F91D38-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| STATUS | RESOURCE | INFO | START DATE | DURATION |\n|--------|----------|------|------------------|----------|\n| | VMware | shredder.jabalabs.cloud | vSphere Distributed Switch VLAN trunked status | 01/07/2026 07:16 AM | 5d 2h |\n| | VMware | shredder.jabalabs.cloud | vSphere Distributed Switch MTU supported status | 01/07/2026 07:16 AM | 5d 2h |"
-}
diff --git a/corpus/.vision-cache/0b78951e1901048d014602a73c1768104b66b34258c44386129da68ce5a4346b.json b/corpus/.vision-cache/0b78951e1901048d014602a73c1768104b66b34258c44386129da68ce5a4346b.json
deleted file mode 100644
index 602d947..0000000
--- a/corpus/.vision-cache/0b78951e1901048d014602a73c1768104b66b34258c44386129da68ce5a4346b.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "0b78951e1901048d014602a73c1768104b66b34258c44386129da68ce5a4346b",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-9916D4B0-7144-4088-98AC-2B2F2E780378-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| CLOUD | COUNT | MEMORY | STORAGE | CPU | PRICE |\n|-------|-------|--------|---------|-----|-------|\n| VMware | 2 | 5.9GiB | 22.0GiB | 1 | $0.07 |"
-}
diff --git a/corpus/.vision-cache/0c265d6963baa34d0ea65afe5ffcd143192c92fc3764d355f479511ea8ea9b3c.json b/corpus/.vision-cache/0c265d6963baa34d0ea65afe5ffcd143192c92fc3764d355f479511ea8ea9b3c.json
deleted file mode 100644
index 3f802da..0000000
--- a/corpus/.vision-cache/0c265d6963baa34d0ea65afe5ffcd143192c92fc3764d355f479511ea8ea9b3c.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "0c265d6963baa34d0ea65afe5ffcd143192c92fc3764d355f479511ea8ea9b3c",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-D08A61BD-C24A-4D73-82C0-45BAEBC26DCB-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| NAME | DESCRIPTION | MONTH TO DATE | PROJECTED TOTAL |\n|------------|--------------------------------------------------|-----------------|------------------|\n| morpheus | | $2,388.69 | $4,227.03 |\n| | | | |\n| | | | |\n| | | | |\n| | | | |"
-}
diff --git a/corpus/.vision-cache/0d7e95ff875283137ebbdf9dcb476e083050c8cfe8caa48f32e17e24ebfdab59.json b/corpus/.vision-cache/0d7e95ff875283137ebbdf9dcb476e083050c8cfe8caa48f32e17e24ebfdab59.json
deleted file mode 100644
index badd647..0000000
--- a/corpus/.vision-cache/0d7e95ff875283137ebbdf9dcb476e083050c8cfe8caa48f32e17e24ebfdab59.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "0d7e95ff875283137ebbdf9dcb476e083050c8cfe8caa48f32e17e24ebfdab59",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-BF328552-F0CB-4A16-89DE-DD5E534DDA21-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Report Type | Description |\n|-------------|-------------|\n| Tenant Inventory Summary | View an inventory of VMs and containers by tenant. |\n| Cloud Usage | View a cloud's usage of storage, memory, and compute resources. |\n| Cloud Usage App Summary | View a cloud's usage of storage, memory, and compute resources by app. |\n| Cloud Usage Instance Type Summary | View a cloud's usage of storage, memory, and compute resources by instance type. |\n| Tenant Usage | View a cloud's usage of storage, memory, and compute resources by tenant. |\n| Amazon Reservation Coverage | View how Amazon EC2 instance types are covered by Reserved Instances. |"
-}
diff --git a/corpus/.vision-cache/108db8dfcfb10934fe7ddde7d91ed6f484ebf9fdf9fe86a72e99a17801f087fd.json b/corpus/.vision-cache/108db8dfcfb10934fe7ddde7d91ed6f484ebf9fdf9fe86a72e99a17801f087fd.json
deleted file mode 100644
index 3b86302..0000000
--- a/corpus/.vision-cache/108db8dfcfb10934fe7ddde7d91ed6f484ebf9fdf9fe86a72e99a17801f087fd.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "108db8dfcfb10934fe7ddde7d91ed6f484ebf9fdf9fe86a72e99a17801f087fd",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-3B425176-5841-4C03-B67D-F6B86603E1CD-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| TAG | WORKLOADS | MEMORY | STORAGE | CPU | PRICE | VALUES |\n|--------------------|-----------|------------|------------|-------|--------|--------|\n| Morpheus Server Id | 37 | 4.6TiB | 73.8TiB | 1 | $299.32| |\n| Morpheus Id | 21 | 2.4TiB | 25.4TiB | 1 | $172.56| |"
-}
diff --git a/corpus/.vision-cache/10bf0d71532812d10314a37a13ab69ad4fdb49490e08156a6a2f993672c3f295.json b/corpus/.vision-cache/10bf0d71532812d10314a37a13ab69ad4fdb49490e08156a6a2f993672c3f295.json
deleted file mode 100644
index 6edab5c..0000000
--- a/corpus/.vision-cache/10bf0d71532812d10314a37a13ab69ad4fdb49490e08156a6a2f993672c3f295.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "10bf0d71532812d10314a37a13ab69ad4fdb49490e08156a6a2f993672c3f295",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-4029426C-1AA2-4873-AE1C-CB4677EFB0F7-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Name | Title | Category |\n|------|-------|----------|\n| | | |"
-}
diff --git a/corpus/.vision-cache/1210d0aee2152b2863303cbc02e5dc82474f4ae783733100719cae9a1a3e9748.json b/corpus/.vision-cache/1210d0aee2152b2863303cbc02e5dc82474f4ae783733100719cae9a1a3e9748.json
deleted file mode 100644
index 999fcc3..0000000
--- a/corpus/.vision-cache/1210d0aee2152b2863303cbc02e5dc82474f4ae783733100719cae9a1a3e9748.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "1210d0aee2152b2863303cbc02e5dc82474f4ae783733100719cae9a1a3e9748",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-66262EA5-76D1-41C6-AE62-C1CF505E9976-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| INVOICE ID | PERIOD | COMPUTE | STORAGE | NETWORK | EXTRA | MTD | TOTAL |\n|------------|--------------|----------|-----------|------------|-----------|------------|------------|\n| 1326425 | September 2020 | $0 | $0 | $0 | $0 | $43.84 | $1,944.02 (Projected) |\n| 1309811 | August 2020 | $1,309.98 | $1,227.51 | $9.56 | $0 | $2,783.84 | $2,783.84 |\n| 1300026 | July 2020 | $1,524.81 | $4,361.13 | $9.64 | $0 | $6,044.27 | $6,044.27 |\n| 1279589 | June 2020 | $4,448.53 | $61.58 | $8.24 | $0 | $4,518.35 | $4,700.00 |\n| 404134 | May 2020 | $0 | $0 | $0 | $0 | $105.37 | $105.37 |\n| 394365 | April 2020 | $0 | $0 | $0 | $0 | $66.99 | $66.99 |\n| 401131 | March 2020 | $0 | $0 | $0 | $0 | $31.58 | $31.58 |\n| 387577 | February 2020 | $0 | $0 | $0 | $0 | $40.62 | $40.62 |\n| 382300 | January 2020 | $0 | $0 | $0 | $0 | $22.31 | $22.31 |"
-}
diff --git a/corpus/.vision-cache/1609a0928a70f0173675bc070f5ec5a975aa7b73c5e5c906e30edfec6e2ffc16.json b/corpus/.vision-cache/1609a0928a70f0173675bc070f5ec5a975aa7b73c5e5c906e30edfec6e2ffc16.json
deleted file mode 100644
index d99a378..0000000
--- a/corpus/.vision-cache/1609a0928a70f0173675bc070f5ec5a975aa7b73c5e5c906e30edfec6e2ffc16.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "1609a0928a70f0173675bc070f5ec5a975aa7b73c5e5c906e30edfec6e2ffc16",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-6493DA77-2790-4079-9636-57D2B389DBCD-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Discovery Info | Z-VRA-10.30.21.61 |\n|----------------|--------------------|\n| Resize Resource | VMware Demo Cluster |\n| Date | 12/14/2018 11:05 AM |\n| Cloud | VMware Demo Cluster |\n| Savings | $50.00/month |\n\n| Icon | Label | Value |\n|------|---------|----------|\n| \ud83d\udd04 | Power | |\n| \u2705 | Status | |\n| \ud83d\udd0d | Type | |\n|\ud83d\udc27 | OS | |\n| VMware| Cloud | |\n\n| Usage Plan | Custom VMware |\n|------------|----------------|\n\n| Icon | Label | Value |\n|------|-----------|-------------|\n| \ud83d\udd04 | Compute | 1% of 100% |\n| \u2705 | Memory | 30.0MB of 3.0GB |\n\n| After Resize | Memory: 1.5GiB |\n|--------------|----------------|\n| Icon | Label | Value |\n| \ud83d\udd04 | Compute | 1% of 100% |\n| \u2705 | Memory | 30.0MB of 1.5GB |\n\n| Buttons | Close | Ignore | Execute |"
-}
diff --git a/corpus/.vision-cache/1b3ef9f9775e56c224ec7226797d34581b7c7ea8f76d5412c39e38a0427dac4a.json b/corpus/.vision-cache/1b3ef9f9775e56c224ec7226797d34581b7c7ea8f76d5412c39e38a0427dac4a.json
deleted file mode 100644
index 4865211..0000000
--- a/corpus/.vision-cache/1b3ef9f9775e56c224ec7226797d34581b7c7ea8f76d5412c39e38a0427dac4a.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "1b3ef9f9775e56c224ec7226797d34581b7c7ea8f76d5412c39e38a0427dac4a",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-F0EDC63A-480C-4013-AC6D-A1C51BA13CC7-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| CONFIGURATION OPTIONS | VALUE |\n|-----------------------|-------|\n| NAME | ${userInitials}-demo-${cloudCode}-${type}-${sequence} |\n| DESCRIPTION | Sample Spud Marketing App |\n| CLOUD | Labs UCS |\n| VERSION | Tomcat 7 jdk 7 |\n| INSTANCE CONFIGURATION| Docker Tomcat |\n| PLAN | 1GB Memory, 10GB Storage |\n| VOLUMES | 10 GB |\n| HOST | Select Server |"
-}
diff --git a/corpus/.vision-cache/1c33e5f4d6f7ee6ac8843fe2ef3d9b5dc61ad2a3bb36ce369414ccbb2c8155e0.json b/corpus/.vision-cache/1c33e5f4d6f7ee6ac8843fe2ef3d9b5dc61ad2a3bb36ce369414ccbb2c8155e0.json
deleted file mode 100644
index 0c932c7..0000000
--- a/corpus/.vision-cache/1c33e5f4d6f7ee6ac8843fe2ef3d9b5dc61ad2a3bb36ce369414ccbb2c8155e0.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "1c33e5f4d6f7ee6ac8843fe2ef3d9b5dc61ad2a3bb36ce369414ccbb2c8155e0",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-1DE90FFC-D78A-4AEC-B168-D1AF1DF3E611-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Purchase a License |\n|---------------------|\n| You must apply a license before using Morpheus.
If you would like to purchase a license or get a free trial please contact us at support@morpheusdata.com,
or call 800-946-9180. |\n| **UPGRADE** |\n\n| Upgrade License Key |\n|---------------------|\n| If you have a new license key, enter it below.
If you need a new license key or would like to upgrade, please contact us at support@morpheusdata.com,
or call 800-946-9180. |\n| **UPDATE** |"
-}
diff --git a/corpus/.vision-cache/1e1ffb9b2f2d9f3380da47af0df1fa81a23eaa844376dc60624d7acd8ee57797.json b/corpus/.vision-cache/1e1ffb9b2f2d9f3380da47af0df1fa81a23eaa844376dc60624d7acd8ee57797.json
deleted file mode 100644
index ca2e988..0000000
--- a/corpus/.vision-cache/1e1ffb9b2f2d9f3380da47af0df1fa81a23eaa844376dc60624d7acd8ee57797.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "1e1ffb9b2f2d9f3380da47af0df1fa81a23eaa844376dc60624d7acd8ee57797",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-3AE2F03E-DBC7-4FC1-BED0-DB5F6B096D9F-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Group | Environment | Cloud | Resource Pool | Plan | Network | Security Group | Name |\n|-------|-------------|-------|----------------|------|----------|-----------------|------|\n| All Clouds | Dev | QA Amazon | labs | T2 Micro - 1 Core, 1GB Memory | 172.31.0.0/20 (subnet-22ba157b) | default | My Workload |"
-}
diff --git a/corpus/.vision-cache/207e759fbbc5b40a0134c1937aa1c98d94b416773bd2c9558fe55fe7ac30f701.json b/corpus/.vision-cache/207e759fbbc5b40a0134c1937aa1c98d94b416773bd2c9558fe55fe7ac30f701.json
deleted file mode 100644
index 869e17e..0000000
--- a/corpus/.vision-cache/207e759fbbc5b40a0134c1937aa1c98d94b416773bd2c9558fe55fe7ac30f701.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "207e759fbbc5b40a0134c1937aa1c98d94b416773bd2c9558fe55fe7ac30f701",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-433AD4AB-C735-49B2-913B-302BF3209248-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Task Name | Start Date | Duration |\n|-----------|------------|----------|\n| Retry Test - Write Pre-Provision Templates | 03/07/2023 03:30 PM | 0s |\n| Retry Test - Write Provision Templates | 03/07/2023 03:30 PM | 0s |\n| Retry Test - Run Task: *Retry Test 1 in *Retry Test Provisioning - Provision | 03/07/2023 03:30 PM | 1s |\n| Retry Test - Run Task: *Retry Test 2 in *Retry Test Provisioning - Provision | 03/07/2023 03:30 PM | 1s |\n| Retry Test - Run Task: *Retry Test 3 in *Retry Test Provisioning - Provision | | |\n| Retry Test - Complete Provisioning | | |"
-}
diff --git a/corpus/.vision-cache/2703f9599273300532c6f5822e484a45c16e41d97d7ee194a4abe566ad03d987.json b/corpus/.vision-cache/2703f9599273300532c6f5822e484a45c16e41d97d7ee194a4abe566ad03d987.json
deleted file mode 100644
index 4803d0d..0000000
--- a/corpus/.vision-cache/2703f9599273300532c6f5822e484a45c16e41d97d7ee194a4abe566ad03d987.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "2703f9599273300532c6f5822e484a45c16e41d97d7ee194a4abe566ad03d987",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-D954DA2F-C2AD-4BD7-B7C3-02CE5AEF0719-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| ORDER PLACED | ITEMS ORDERED | ORDER STATUS |\n|--------------|---------------|--------------|\n| 09/22/2020 | 1 | Complete |"
-}
diff --git a/corpus/.vision-cache/2a7cadedede3d9802e8b87c3bc55cc40a0f248e46504a464fad1391558dc0828.json b/corpus/.vision-cache/2a7cadedede3d9802e8b87c3bc55cc40a0f248e46504a464fad1391558dc0828.json
deleted file mode 100644
index d0df800..0000000
--- a/corpus/.vision-cache/2a7cadedede3d9802e8b87c3bc55cc40a0f248e46504a464fad1391558dc0828.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "2a7cadedede3d9802e8b87c3bc55cc40a0f248e46504a464fad1391558dc0828",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-EED20D75-2987-4570-A0F2-5AD920F49D1D-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Instance | Type | Address |\n|----------|------------|--------------------|\n| | | |"
-}
diff --git a/corpus/.vision-cache/35fb2d3c6bf82a8ca417866184a1c93c40c0551c9f582ccbb8e8cf54dccbb9e1.json b/corpus/.vision-cache/35fb2d3c6bf82a8ca417866184a1c93c40c0551c9f582ccbb8e8cf54dccbb9e1.json
deleted file mode 100644
index d26056d..0000000
--- a/corpus/.vision-cache/35fb2d3c6bf82a8ca417866184a1c93c40c0551c9f582ccbb8e8cf54dccbb9e1.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "35fb2d3c6bf82a8ca417866184a1c93c40c0551c9f582ccbb8e8cf54dccbb9e1",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-C731E3A8-F507-477B-93AB-71BC98DA37A0-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| INSTANCE TYPE | ON DEMAND HOURS | RESERVED HOURS | TOTAL HOURS | COVERAGE |\n|-------------------------|------------------|-----------------|-------------|----------|\n| DV2/DSV2 SERIES | 384.15 | 0.0 | 384.15 | 0.0% |\n| A SERIES WINDOWS | 1,366.82 | 0.0 | 1,366.82 | 0.0% |\n| A SERIES BASIC | 1,556.2 | 0.0 | 1,556.2 | 0.0% |\n| AV2 SERIES | 178.33 | 0.0 | 178.33 | 0.0% |\n| BS SERIES | 1,534.95 | 0.0 | 1,534.95 | 0.0% |\n| AV2 SERIES WINDOWS | 3.07 | 0.0 | 3.07 | 0.0% |\n| BS SERIES WINDOWS | 381.92 | 0.0 | 381.92 | 0.0% |\n| A SERIES | 383.35 | 0.0 | 383.35 | 0.0% |\n| DV2/DSV2 SERIES WINDOWS | 2.47 | 0.0 | 2.47 | 0.0% |"
-}
diff --git a/corpus/.vision-cache/3e5c1feb5480ae7eb79b7c1b263f5e32ff360c14725cc8b966a93f60368fb119.json b/corpus/.vision-cache/3e5c1feb5480ae7eb79b7c1b263f5e32ff360c14725cc8b966a93f60368fb119.json
deleted file mode 100644
index 9746586..0000000
--- a/corpus/.vision-cache/3e5c1feb5480ae7eb79b7c1b263f5e32ff360c14725cc8b966a93f60368fb119.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "3e5c1feb5480ae7eb79b7c1b263f5e32ff360c14725cc8b966a93f60368fb119",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-EF84CC50-D2E4-4906-9051-655D7B15CE65-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| TYPE | NAME | TECHNOLOGY | LABELS |\n|------------|----------------|-------------|----------------|\n| Resource | *test | Amazon | aws |\n| Resource | Custom Amazon CentOS | | centos |\n| Resource | Custom App | | app, aws, vmware |\n| Resource | Custom VMware Ubuntu | | ubuntu, vmware |"
-}
diff --git a/corpus/.vision-cache/42588cd48ecf67c8688139c09bbb9676714c4512587e6e98f943abc6ca6e64e0.json b/corpus/.vision-cache/42588cd48ecf67c8688139c09bbb9676714c4512587e6e98f943abc6ca6e64e0.json
deleted file mode 100644
index b3eed27..0000000
--- a/corpus/.vision-cache/42588cd48ecf67c8688139c09bbb9676714c4512587e6e98f943abc6ca6e64e0.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "42588cd48ecf67c8688139c09bbb9676714c4512587e6e98f943abc6ca6e64e0",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-54937FF3-952A-40DE-8C06-8E193416776A-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Date | Memory Usage (GB) |\n|------------|--------------------|\n| Apr-21 | 0 |\n| Apr-24 | 8500 |\n| Apr-27 | 9000 |\n| Apr-30 | 9500 |\n| May-03 | 90000 |\n| May-06 | 95000 |\n| May-09 | 100000 |\n| May-12 | 95000 |\n| May-15 | 100000 |\n| May-18 | 105000 |\n| May-21 | 85000 |\n| May-24 | 90000 |\n| May-27 | 95000 |\n| Jun-02 | 90000 |\n| Jun-05 | 85000 |\n| Jun-08 | 80000 |\n| Jun-11 | 85000 |\n| Jun-14 | 80000 |\n| Jun-17 | 85000 |\n| Jun-20 | 90000 |"
-}
diff --git a/corpus/.vision-cache/44cacfa1e7cf2dc66d8c5311b72b3c686ec565d947f3b1d26ad502770b92f094.json b/corpus/.vision-cache/44cacfa1e7cf2dc66d8c5311b72b3c686ec565d947f3b1d26ad502770b92f094.json
deleted file mode 100644
index 9de87fb..0000000
--- a/corpus/.vision-cache/44cacfa1e7cf2dc66d8c5311b72b3c686ec565d947f3b1d26ad502770b92f094.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "44cacfa1e7cf2dc66d8c5311b72b3c686ec565d947f3b1d26ad502770b92f094",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-77399E18-27B9-465D-885C-F34C86B2EA19-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Job Configuration | Value |\n|-------------------|-------|\n| SECURITY PACKAGE | scap security bundle 0.1.51 |\n| SCAN CHECKLIST | /scap-security-guide-0.1.51/ssg-ubuntu1804-ds.xml |\n| SECURITY PROFILE | xccdf_org.ssgproject.content_profile_cis |\n\n| Execution Config | Value |\n|--------------------|-------|\n| SCHEDULE | Daily |\n| RUN NOW | (unchecked) |\n| CONTEXT TYPE | Server |\n| CONTEXT SERVER | de-ubuntu-1 |"
-}
diff --git a/corpus/.vision-cache/4af3aed5fcf9f5c13c9786cf0687bd2410e8248df9589e41ed443a75b1a1792e.json b/corpus/.vision-cache/4af3aed5fcf9f5c13c9786cf0687bd2410e8248df9589e41ed443a75b1a1792e.json
deleted file mode 100644
index bbdec83..0000000
--- a/corpus/.vision-cache/4af3aed5fcf9f5c13c9786cf0687bd2410e8248df9589e41ed443a75b1a1792e.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "4af3aed5fcf9f5c13c9786cf0687bd2410e8248df9589e41ed443a75b1a1792e",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-BA459071-AEAD-4E96-8DB9-FD67DDE9ABC5-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Field | Description |\n|--------------|-----------------------------------------------------------------------------|\n| NAME | My Task |\n| CODE | (empty) |\n| LABELS | A comma-separated list of labels that can be used to group/organize items. |\n| TYPE | Python Script |\n| RESULT_TYPE | None |\n| SOURCE | Local |\n| CONTENT | morpheus['cypher']['read']('') |"
-}
diff --git a/corpus/.vision-cache/4f648ba912d17e2d114818c97455de805b580e24c5dde16c76e1606b0ea5dc8d.json b/corpus/.vision-cache/4f648ba912d17e2d114818c97455de805b580e24c5dde16c76e1606b0ea5dc8d.json
deleted file mode 100644
index 4f84a23..0000000
--- a/corpus/.vision-cache/4f648ba912d17e2d114818c97455de805b580e24c5dde16c76e1606b0ea5dc8d.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "4f648ba912d17e2d114818c97455de805b580e24c5dde16c76e1606b0ea5dc8d",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-01557155-5F51-4E18-9423-80740E675D88-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Name: | morpheus-export |\n| --- | --- |\n| Type: | GitHub |\n| Default Branch: | main |\n| Owner: | aharker |\n| Code Language: | |\n\n| Organization: | ahark86 |\n| Location: | https://github.com/ahark86/morpheus-export |"
-}
diff --git a/corpus/.vision-cache/51edc81040509f7e2b617b7d544ab7219f73dcf0e91a87b09adfc9db624f9e89.json b/corpus/.vision-cache/51edc81040509f7e2b617b7d544ab7219f73dcf0e91a87b09adfc9db624f9e89.json
deleted file mode 100644
index 3eef0c2..0000000
--- a/corpus/.vision-cache/51edc81040509f7e2b617b7d544ab7219f73dcf0e91a87b09adfc9db624f9e89.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "51edc81040509f7e2b617b7d544ab7219f73dcf0e91a87b09adfc9db624f9e89",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-BC2102C2-6D1A-4EC2-8F51-173EAE0CE091-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Groups | NAME | LOCATION | DATACENTER | MONTH TO DATE | PROJECTED TOTAL |\n|--------|------|----------|------------|---------------|-----------------|\n| | | | | | |\n| | | | | $24,865.05 | $24,865.05 |\n| | | | | $61.86 | $104.31 |\n| | | | | $30.49 | $30.49 |\n| | | | | $26.04 | $43.21 |\n| | | Denver | | $11.72 | $11.72 |"
-}
diff --git a/corpus/.vision-cache/548669a3aed4ff4080040ca19e2c2f4dce295144ff3532e60318c6d7926ad9e8.json b/corpus/.vision-cache/548669a3aed4ff4080040ca19e2c2f4dce295144ff3532e60318c6d7926ad9e8.json
deleted file mode 100644
index e4f1e89..0000000
--- a/corpus/.vision-cache/548669a3aed4ff4080040ca19e2c2f4dce295144ff3532e60318c6d7926ad9e8.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "548669a3aed4ff4080040ca19e2c2f4dce295144ff3532e60318c6d7926ad9e8",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-4A12A8C3-AB86-4D4A-AF4E-432D5D9515BA-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Month | Budget | Actual |\n|-------|---------|--------|\n| January | $83 | $115 |\n| February | $0 | $0 |\n| March | $0 | $0 |\n| April | $0 | $0 |\n| May | $0 | $0 |\n| June | $0 | $0 |\n| July | $0 | $0 |\n| August | $0 | $0 |\n| September | $0 | $0 |\n| October | $0 | $0 |\n| November| $0 | $0 |\n| December| $83 | $0 |"
-}
diff --git a/corpus/.vision-cache/567805a79678184197d713468483ccaa269343479d937c1454e3aadf32538d50.json b/corpus/.vision-cache/567805a79678184197d713468483ccaa269343479d937c1454e3aadf32538d50.json
deleted file mode 100644
index 8175fa9..0000000
--- a/corpus/.vision-cache/567805a79678184197d713468483ccaa269343479d937c1454e3aadf32538d50.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "567805a79678184197d713468483ccaa269343479d937c1454e3aadf32538d50",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-DE8D2A86-CAB3-4D94-9D4C-83C5FA49585A-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Start Date | Duration | User |\n|------------|----------|--------|\n| 01/12/2026 05:30 AM | 1m 59s | ttran |\n| 01/12/2026 05:30 AM | 2m 47s | ttran |\n| 01/12/2026 05:30 AM | 2m 42s | ttran |\n| 01/12/2026 05:30 AM | 28m 10s | ttran |\n| 01/12/2026 05:30 AM | 2m 40s | waked |"
-}
diff --git a/corpus/.vision-cache/5a948621965266305852338ac7e8184288d21d148f3ea937d35e93973bc980b1.json b/corpus/.vision-cache/5a948621965266305852338ac7e8184288d21d148f3ea937d35e93973bc980b1.json
deleted file mode 100644
index 2b1dea7..0000000
--- a/corpus/.vision-cache/5a948621965266305852338ac7e8184288d21d148f3ea937d35e93973bc980b1.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "5a948621965266305852338ac7e8184288d21d148f3ea937d35e93973bc980b1",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-2D5FF1AC-0C5C-4977-BFC3-19FBA953BC8F-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Appliance Settings | Description |\n|--------------------|-------------|\n| Appliance URL | https://appliance.url.com |\n| Internal Appliance URL (PXE) | | For PXE-Boot your appliance needs to be routable directly with minimal NAT masquerading. This allows one to override the default appliance url endpoint for use by the PXE Server. If this is unset, the default appliance url will be used instead. |"
-}
diff --git a/corpus/.vision-cache/5ec4381c5918e8f5c2e313a88fe4a12bca553cf7e019d798e3cc2f9d909de3fd.json b/corpus/.vision-cache/5ec4381c5918e8f5c2e313a88fe4a12bca553cf7e019d798e3cc2f9d909de3fd.json
deleted file mode 100644
index 2ea923c..0000000
--- a/corpus/.vision-cache/5ec4381c5918e8f5c2e313a88fe4a12bca553cf7e019d798e3cc2f9d909de3fd.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "5ec4381c5918e8f5c2e313a88fe4a12bca553cf7e019d798e3cc2f9d909de3fd",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-627980F3-725B-4765-8CF0-89FD087667C8-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Component | Description |\n|----------|-------------|\n| Load Balancer | Manages traffic between clients and servers |\n| Morpheus Nodes | Nodes that run the Morpheus application |\n| RabbitMQ | Message broker for communication between nodes |\n| Elastic | Search engine and analytics platform |\n| App Node 1, App Node 2, App Node 3 | Application nodes running applications |\n| DB Node 1, DB Node 2, DB Node 3 | Database nodes storing data |\n| Database Cluster | A cluster of database nodes for redundancy and scalability |\n| Shared Storage | Central storage shared by all components |"
-}
diff --git a/corpus/.vision-cache/604e1c401bf8686eec90e60523bded08256a7e1f21701df0448a7f07f642d1e0.json b/corpus/.vision-cache/604e1c401bf8686eec90e60523bded08256a7e1f21701df0448a7f07f642d1e0.json
deleted file mode 100644
index 850c3e0..0000000
--- a/corpus/.vision-cache/604e1c401bf8686eec90e60523bded08256a7e1f21701df0448a7f07f642d1e0.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "604e1c401bf8686eec90e60523bded08256a7e1f21701df0448a7f07f642d1e0",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-BF0ECE3F-331E-4BDF-9CF3-8DA3BAF19EFA-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Field | Description |\n|--------------|-----------------------------------------------------------------------------|\n| NAME | Text field for entering a name |\n| START | Date and time picker for selecting start date |\n| END | Date and time picker for selecting end date |\n| GROUP | Dropdown menu to select a group |\n| CLOUD | Dropdown menu to select a cloud |\n| TAGS | Text field for entering tags |\n| EXCLUDE_TAGS | Text field for excluding tags |\n| TENANT | Dropdown menu with options: All |\n| SCHEDULE | Dropdown menu with options: Select, Date And Time, Daily, Daily At Midnight, Hourly, Weekly On Sunday At Midnight |"
-}
diff --git a/corpus/.vision-cache/6ae068ce8fefe79d0f4c1888e5e0833609dcd8497008d9189becf2522d5c7266.json b/corpus/.vision-cache/6ae068ce8fefe79d0f4c1888e5e0833609dcd8497008d9189becf2522d5c7266.json
deleted file mode 100644
index c31d22c..0000000
--- a/corpus/.vision-cache/6ae068ce8fefe79d0f4c1888e5e0833609dcd8497008d9189becf2522d5c7266.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "6ae068ce8fefe79d0f4c1888e5e0833609dcd8497008d9189becf2522d5c7266",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-2EECD2F1-36D5-4E56-B12D-99872F54B075-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Instance Name | SSH: IP Address | Version | Status | Containers |\n|---------------|-----------------|---------|--------|------------|\n| MORPHEUS-HA-AP1 | 10.30.20.181:22, 10.30.20.62:22 | 7.3 | Running | 2 |\n| JW-CENTOS-AHV | 10.30.20.165:22, 10.30.20.91:22, 10.30.20.149:22 | 7.3 | Running | 3 |\n| JW-CENTOS-AHV-1 | 10.30.20.135:22, 10.30.20.37:22, 10.30.20.52:22 | 7.3 | Running | 3 |\n| JW-CENTOS-AHV-2 | 10.30.20.104:22 | 7.3 | Running | 1 |\n| MORPHEUS-HA-DB | 10.30.20.153:22, 10.30.20.139:22, 10.30.20.196:22 | 7.3 | Running | 3 |\n| MORPHEUS-HA-MQ | 10.30.20.129:22, 10.30.20.58:22 | 7.3 | Running | 2 |\n| MORPHEUS-HA-MQ-LB-1 | 10.30.20.53:22 | 7.3 | Running | 1 |"
-}
diff --git a/corpus/.vision-cache/6bbeb863375cfc066ec66e5346cc9c13089ddb39bf4a55ede66c261b88c3488e.json b/corpus/.vision-cache/6bbeb863375cfc066ec66e5346cc9c13089ddb39bf4a55ede66c261b88c3488e.json
deleted file mode 100644
index 67ae035..0000000
--- a/corpus/.vision-cache/6bbeb863375cfc066ec66e5346cc9c13089ddb39bf4a55ede66c261b88c3488e.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "6bbeb863375cfc066ec66e5346cc9c13089ddb39bf4a55ede66c261b88c3488e",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-98D09465-88F7-420B-AEF8-80393CC3A8B7-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| POWER | OS | NAME | TYPE | CLOUD | PRICE | CPU UTILIZATION |\n|-------|----|------|------|-------|-------|------------------|\n| ? | ? | aa-sb-morpheus-centos-4110 | Managed VM | VMware vCenter | $51.66 | 3, 6, 25 |\n| | | labs_west-chef-web-01a | Discovered | AWS MorpheusDemo | $51.80 | |"
-}
diff --git a/corpus/.vision-cache/715e2960eaca4afcc6d554ae8e1921b263b5cb2f2be0f73c312b04105c90b502.json b/corpus/.vision-cache/715e2960eaca4afcc6d554ae8e1921b263b5cb2f2be0f73c312b04105c90b502.json
deleted file mode 100644
index c4f7a05..0000000
--- a/corpus/.vision-cache/715e2960eaca4afcc6d554ae8e1921b263b5cb2f2be0f73c312b04105c90b502.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "715e2960eaca4afcc6d554ae8e1921b263b5cb2f2be0f73c312b04105c90b502",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-ED6FCF79-BB81-4C2B-B4A6-4DCB7357CFB5-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| ORDER PLACED | ITEMS ORDERED | ORDER STATUS |\n|--------------|---------------|--------------|\n| 09/22/2020 | 1 | Complete |"
-}
diff --git a/corpus/.vision-cache/71bf4d3e41d1940bc52fdebcf1fe0fc184602a27e59ab03ff346024982fe6e4c.json b/corpus/.vision-cache/71bf4d3e41d1940bc52fdebcf1fe0fc184602a27e59ab03ff346024982fe6e4c.json
deleted file mode 100644
index b24529e..0000000
--- a/corpus/.vision-cache/71bf4d3e41d1940bc52fdebcf1fe0fc184602a27e59ab03ff346024982fe6e4c.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "71bf4d3e41d1940bc52fdebcf1fe0fc184602a27e59ab03ff346024982fe6e4c",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-C67DA833-C730-4887-9672-7E63FABC0841-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| TYPE | NAME | INSTANCES | GROUPS | CLOUDS | COUNT |\n|------------|----------------|-----------|--------|--------|-------|\n| MISSING LOGO | [Name redacted] | 1 | 1 | 1 | 1 |\n| MISSING LOGO | [Name redacted] | 1 | 1 | 1 | 1 |"
-}
diff --git a/corpus/.vision-cache/8745139b63ba1f68e0e50274b92c3777e0b66d6189f64f40209d921d450e2e47.json b/corpus/.vision-cache/8745139b63ba1f68e0e50274b92c3777e0b66d6189f64f40209d921d450e2e47.json
deleted file mode 100644
index d4407eb..0000000
--- a/corpus/.vision-cache/8745139b63ba1f68e0e50274b92c3777e0b66d6189f64f40209d921d450e2e47.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "8745139b63ba1f68e0e50274b92c3777e0b66d6189f64f40209d921d450e2e47",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-D2F4F5EE-5377-4E4A-A6E8-DAD6ED4FBD80-high.gif",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| LUSH | +N | +E |\n|------|----|----|"
-}
diff --git a/corpus/.vision-cache/9179cf63689fcca101bf6ef9a26ab5aeaa027cc3c07721776e6cc0e33f02f846.json b/corpus/.vision-cache/9179cf63689fcca101bf6ef9a26ab5aeaa027cc3c07721776e6cc0e33f02f846.json
deleted file mode 100644
index a5214fb..0000000
--- a/corpus/.vision-cache/9179cf63689fcca101bf6ef9a26ab5aeaa027cc3c07721776e6cc0e33f02f846.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "9179cf63689fcca101bf6ef9a26ab5aeaa027cc3c07721776e6cc0e33f02f846",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-1897DAD3-23E6-4D44-8331-93C40D4FD9FA-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| NAME | DESCRIPTION |\n| --- | --- |\n| ahark86/morpheus-export | |\n| IMPORT/EXPORT | Manual export |\n| PATH | prod |\n| EXPORT LABEL FILTER | prod |"
-}
diff --git a/corpus/.vision-cache/93c24b083648b0058e838dd0f7c069b7afde7c67173ea2e4ecd5aa2c11487c7e.json b/corpus/.vision-cache/93c24b083648b0058e838dd0f7c069b7afde7c67173ea2e4ecd5aa2c11487c7e.json
deleted file mode 100644
index 6b312c4..0000000
--- a/corpus/.vision-cache/93c24b083648b0058e838dd0f7c069b7afde7c67173ea2e4ecd5aa2c11487c7e.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "93c24b083648b0058e838dd0f7c069b7afde7c67173ea2e4ecd5aa2c11487c7e",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-102FBE32-895E-4617-80D4-AA313E7BB572-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Workload Type | Cost |\n|---------------|------|\n| CentOS | $238.60 |\n| Nutanix | $39.17 |\n| Ubuntu | $33.58 |\n| Other | $13.10 |\n| Another | $3.18 |\n| Yet Another | $2.44 |\n\n| Workload Type | Cost |\n|---------------|------|\n| 2 vCPU, 8GB Memory | $51.55 |\n| 2 CPU, 16GB Memory | $51.52 |\n| 2 CPU, 8GB Memory | $26.15 |\n| m1.large | $14.65 |\n| 1 CPU, 4GB Memory | $13.10 |\n| 1 vCPU, 4GB Memory | $13.06 |"
-}
diff --git a/corpus/.vision-cache/94142b2fc15a4a671483c963665c0ae25b172c6458e6924d32f1ef5bfe8e4dfa.json b/corpus/.vision-cache/94142b2fc15a4a671483c963665c0ae25b172c6458e6924d32f1ef5bfe8e4dfa.json
deleted file mode 100644
index 87a2b59..0000000
--- a/corpus/.vision-cache/94142b2fc15a4a671483c963665c0ae25b172c6458e6924d32f1ef5bfe8e4dfa.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "94142b2fc15a4a671483c963665c0ae25b172c6458e6924d32f1ef5bfe8e4dfa",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-47300BA8-9B05-428D-835A-1975B04DE84E-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Task Name | Start Date | Duration | User |\n|-----------|------------------|------------|--------------|\n| Local - Run Workflow: Workflow kill test | 03/14/2023 01:54 PM | 3m 41s | Tenant Harker |\n| Local - Run Task: Task kill test in Workflow kill test - Operation | 03/14/2023 01:57 PM | 44s | |\n| Local - Run Task: Task kill test in Workflow kill test - Operation | 03/14/2023 01:57 PM | 40s | |"
-}
diff --git a/corpus/.vision-cache/973245eaefc41aa7a9b96511fedb11e09f47e2105935309777c8eb6eae22f19a.json b/corpus/.vision-cache/973245eaefc41aa7a9b96511fedb11e09f47e2105935309777c8eb6eae22f19a.json
deleted file mode 100644
index 4312029..0000000
--- a/corpus/.vision-cache/973245eaefc41aa7a9b96511fedb11e09f47e2105935309777c8eb6eae22f19a.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "973245eaefc41aa7a9b96511fedb11e09f47e2105935309777c8eb6eae22f19a",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-035126CA-FDE7-492E-842A-094558CB1655-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| ID | START DATE | END DATE | USAGE TYPE | USAGE | RATE | UNIT | COST | ITEM NAME |\n|----------|----------------------|----------------------|-------------------------------------------------|----------------|----------|---------|--------|-----------|\n| 1612407 | 8/1/20 12:00 AM | 8/30/20 1:00 PM | USW1-CW:Requests | 1.0078647E7 | 1.0E-5 | Requests | $100.79| QA Amazon |\n| 1614136 | 8/1/20 6:00 PM | 8/1/20 7:00 PM | USW1-DataTransfer-Out-Bytes | 9.4892E-6 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1614137 | 8/1/20 6:00 PM | 8/1/20 7:00 PM | USW1-DataTransfer-Out-Bytes | 7.7188E-6 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1614138 | 8/1/20 6:00 PM | 8/1/20 7:00 PM | USW1-LCUUsage | 1.833333E-4 | 0.007999995| LCU-Hrs | $0.00 | QA Amazon |\n| 1614139 | 8/1/20 6:00 PM | 8/1/20 7:00 PM | USW1-LoadBalancerUsage | 1.0 | 0.0252 | Hrs | $0.03 | QA Amazon |\n| 1614140 | 8/1/20 6:00 PM | 8/1/20 7:00 PM | USW1-LoadBalancerUsage | 1.0 | 0.0252 | Hrs | $0.03 | QA Amazon |\n| 1619670 | 8/1/20 7:00 PM | 8/24/20 10:00 PM | us-west-1-KMS-Requests | 39.0 | 3.0E-6 | Requests| $0.00 | QA Amazon |\n| 1617343 | 8/3/20 3:00 PM | 8/30/20 1:00 PM | USW1-LoadBalancerUsage | 646.0 | 0.0252 | Hrs | $16.28 | QA Amazon |\n| 1620003 | 8/5/20 4:00 PM | 8/5/20 5:00 PM | USW1-DataProcessing-Bytes | 6.1E-7 | 0.008 | GB | $0.00 | QA Amazon |\n| 1620006 | 8/5/20 4:00 PM | 8/5/20 5:00 PM | USW1-LCUUsage | 2.055556E-4 | 0.007999995| LCU-Hrs | $0.00 | QA Amazon |\n| 1620008 | 8/5/20 4:00 PM | 8/5/20 5:00 PM | USW1-LoadBalancerUsage | 1.0 | 0.0252 | Hrs | $0.03 | QA Amazon |\n| 1620005 | 8/5/20 4:00 PM | 8/5/20 6:00 PM | USW1-DataTransfer-Out-Bytes | 6.9551E-6 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1620004 | 8/5/20 4:00 PM | 8/6/20 7:00 AM | USW1-DataTransfer-Out-Bytes | 3.46508E-5 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1620007 | 8/5/20 4:00 PM | 8/6/20 7:00 AM | USW1-LoadBalancerUsage | 2.0 | 0.028 | Hrs | $0.06 | QA Amazon |\n| 1620726 | 8/6/20 6:00 AM | 8/6/20 7:00 AM | USW1-DataTransfer-Out-Bytes | 7.5875E-6 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1620727 | 8/6/20 6:00 AM | 8/6/20 7:00 AM | USW1-LCUUsage | 2.055556E-4 | 0.007999995| LCU-Hrs | $0.00 | QA Amazon |\n| 1620728 | 8/6/20 6:00 AM | 8/6/20 7:00 AM | USW1-LoadBalancerUsage | 1.0 | 0.0252 | Hrs | $0.03 | QA Amazon |\n| 1621067 | 8/6/20 3:00 PM | 8/6/20 4:00 PM | USW1-DataTransfer-Out-Bytes | 2.282E-7 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1623759 | 8/11/20 8:00 AM | 8/11/20 9:00 AM | USW1-DataTransfer-Out-Bytes | 1.08387E-5 | 0.0897631338| GB | $0.00 | QA Amazon |\n| 1623762 | 8/11/20 8:00 AM | 8/11/20 9:00 AM | USW1-LoadBalancerUsage | 1.0 | 0.028 | Hrs | $0.03 | QA Amazon |"
-}
diff --git a/corpus/.vision-cache/abb0491f82bcc5cfe483f5e38061f48818d04d2f562c27e53164d8e0b2e6e56b.json b/corpus/.vision-cache/abb0491f82bcc5cfe483f5e38061f48818d04d2f562c27e53164d8e0b2e6e56b.json
deleted file mode 100644
index 0e7c6d4..0000000
--- a/corpus/.vision-cache/abb0491f82bcc5cfe483f5e38061f48818d04d2f562c27e53164d8e0b2e6e56b.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "abb0491f82bcc5cfe483f5e38061f48818d04d2f562c27e53164d8e0b2e6e56b",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-24D6CCD6-E864-4CA6-8D91-5EFDFB50CB33-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| TYPE | NAME | DETAILS | ACTIVE |\n|------|------|---------|--------|"
-}
diff --git a/corpus/.vision-cache/af03ebcfe831b7c296a01811b694e6b057cf7a512bd8f606a71fc284b2115664.json b/corpus/.vision-cache/af03ebcfe831b7c296a01811b694e6b057cf7a512bd8f606a71fc284b2115664.json
deleted file mode 100644
index 91b7c9a..0000000
--- a/corpus/.vision-cache/af03ebcfe831b7c296a01811b694e6b057cf7a512bd8f606a71fc284b2115664.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "af03ebcfe831b7c296a01811b694e6b057cf7a512bd8f606a71fc284b2115664",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-D7C44885-681F-4B92-8D83-E5EB52F25660-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Month | Budget | Actual |\n|-------|---------|--------|\n| January | $0 | $45 |\n| February| $0 | $42 |\n| March | $0 | $42 |\n| April | $0 | $45 |\n| May | $0 | $45 |\n| June | $0 | $53 |"
-}
diff --git a/corpus/.vision-cache/af9cf8855a81bb32c66391bdc66ae73451cc81ee29bfc65c529dc45b4500d5c0.json b/corpus/.vision-cache/af9cf8855a81bb32c66391bdc66ae73451cc81ee29bfc65c529dc45b4500d5c0.json
deleted file mode 100644
index 8a63d6c..0000000
--- a/corpus/.vision-cache/af9cf8855a81bb32c66391bdc66ae73451cc81ee29bfc65c529dc45b4500d5c0.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "af9cf8855a81bb32c66391bdc66ae73451cc81ee29bfc65c529dc45b4500d5c0",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-39F2C925-F3CB-4E65-B5A6-B5B515D2A1F6-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Field | Value |\n|-------------|----------------------|\n| START | 08/21/2020 |\n| END | 08/24/2020 |\n| GROUP | Select |\n| CLOUD | Select |\n| TAGS | |\n| EXCLUDE TAGS| |\n| TENANT | All |"
-}
diff --git a/corpus/.vision-cache/b41f37d37b3db8c897136ad7a178f6890f06ace7eb582bbf90575e81f1f1ed08.json b/corpus/.vision-cache/b41f37d37b3db8c897136ad7a178f6890f06ace7eb582bbf90575e81f1f1ed08.json
deleted file mode 100644
index 12294d4..0000000
--- a/corpus/.vision-cache/b41f37d37b3db8c897136ad7a178f6890f06ace7eb582bbf90575e81f1f1ed08.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "b41f37d37b3db8c897136ad7a178f6890f06ace7eb582bbf90575e81f1f1ed08",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-18A42C5E-8C61-4ADA-AF78-23E743A230ED-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Field | Value |\n|--------------|----------------------|\n| NAME | |\n| DESCRIPTION | |\n| ENABLED | \u2714 |\n| SCOPE | Account |\n| PERIOD | Year |\n| YEAR | Custom |\n| START DATE | 01/2021 |\n| END DATE | 12/2021 |\n| INTERVAL | Month |\n| JANUARY | 0.0 |"
-}
diff --git a/corpus/.vision-cache/b61946d04e7a92314a9285e9ecfd58a4cce6722cf0b5c751f1e6ad563d3c7a23.json b/corpus/.vision-cache/b61946d04e7a92314a9285e9ecfd58a4cce6722cf0b5c751f1e6ad563d3c7a23.json
deleted file mode 100644
index e0ef5dc..0000000
--- a/corpus/.vision-cache/b61946d04e7a92314a9285e9ecfd58a4cce6722cf0b5c751f1e6ad563d3c7a23.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "b61946d04e7a92314a9285e9ecfd58a4cce6722cf0b5c751f1e6ad563d3c7a23",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-E8A3A8C8-27F1-48F1-8B98-2AF3AAE6E121-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Job Summary | |\n| --- | --- |\n| NAME | Scan Job |\n| JOB TYPE | Security Scan Job |"
-}
diff --git a/corpus/.vision-cache/b778bd19773b2cc4a96b7f15d11ab327060674c9198d3c6aee437f004f20f72a.json b/corpus/.vision-cache/b778bd19773b2cc4a96b7f15d11ab327060674c9198d3c6aee437f004f20f72a.json
deleted file mode 100644
index 04fd663..0000000
--- a/corpus/.vision-cache/b778bd19773b2cc4a96b7f15d11ab327060674c9198d3c6aee437f004f20f72a.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "b778bd19773b2cc4a96b7f15d11ab327060674c9198d3c6aee437f004f20f72a",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-19673F2B-9D42-4067-BC83-078B0046D28B-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| USERNAME | MONTH TO DATE | PROJECTED TOTAL |\n|----------|---------------|-----------------|\n| discovered | $673 | $1,092 |"
-}
diff --git a/corpus/.vision-cache/bfc8e63b481b571301d69af6c7102aaf86c00550e999768e5bcb7d12c44451f7.json b/corpus/.vision-cache/bfc8e63b481b571301d69af6c7102aaf86c00550e999768e5bcb7d12c44451f7.json
deleted file mode 100644
index edfa575..0000000
--- a/corpus/.vision-cache/bfc8e63b481b571301d69af6c7102aaf86c00550e999768e5bcb7d12c44451f7.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "bfc8e63b481b571301d69af6c7102aaf86c00550e999768e5bcb7d12c44451f7",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-F0F0DA3A-4058-45D6-AECA-8A5BEF62FDBA-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Getting Started With The Wiki |\n| --- |\n| Welcome to the Wiki! This service ties into assets throughout the environment. Create pages for instances, hosts, groups, clouds, and even clusters directly on their detail pages. Or, just create general notes pages here in the centralized Wiki section in Markdown format. |\n| Creating your first page is as simple as clicking the **Create Page** button. Write down some content, give the page a title, and click the save button. The wiki will also keep track of who last edited a page and when. The beauty of this wiki is its clean and easy to write down notes related to various parts of your application deployment or infrastructure without going to an external tool. |\n| **Create A Homepage** |\n| The wiki provides an easy way to replace this page with a new default page. Simply create a page with the title **Home**. When that page is created, it will become the new default page for the Wiki and visible by all the users that have access to this section. |\n| **Secure** |\n| All wiki pages are encrypted using AES-256 bit encryption. Though we don't advise storing passwords in a wiki document (there's services like Cypher for that). Role-based access control also can properly restrict access to content related to instances or hosts the user may not have access to. |\n\n| Pages |\n| --- |\n| Search | Page Index |"
-}
diff --git a/corpus/.vision-cache/c044d63eeace101d9f0a0bf4ac948d9b764660d4d08db49876e99ab49ed7d76b.json b/corpus/.vision-cache/c044d63eeace101d9f0a0bf4ac948d9b764660d4d08db49876e99ab49ed7d76b.json
deleted file mode 100644
index ef03428..0000000
--- a/corpus/.vision-cache/c044d63eeace101d9f0a0bf4ac948d9b764660d4d08db49876e99ab49ed7d76b.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "c044d63eeace101d9f0a0bf4ac948d9b764660d4d08db49876e99ab49ed7d76b",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-7D08D7CC-C9FD-4013-9B64-78A4F9C8B639-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| INVOICE ID | TYPE | REFERENCE | CLOUD | PERIOD | START DATE | END DATE | MTD PRICE | TOTAL PRICE |\n|------------|------------|-----------|------------|----------------|----------------------------|----------------------------|-------------|-------------|\n| 282029 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.12 | $0.15 |\n| 292790 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.00 | $0.00 |\n| 292809 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.00 | $0.00 |\n| 282143 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.26 | $0.32 |\n| 287435 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.00 | $0.00 |\n| 292704 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.12 | $0.48 |\n| 282114 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.24 | $0.29 |\n| 292239 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.00 | $0.00 |\n| 285619 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM | $0.00 | $0.00 |"
-}
diff --git a/corpus/.vision-cache/c4910edb2db46d2d544dab398aac9e8266d757db51c92c22ea2333b6d5d5daad.json b/corpus/.vision-cache/c4910edb2db46d2d544dab398aac9e8266d757db51c92c22ea2333b6d5d5daad.json
deleted file mode 100644
index 565204d..0000000
--- a/corpus/.vision-cache/c4910edb2db46d2d544dab398aac9e8266d757db51c92c22ea2333b6d5d5daad.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "c4910edb2db46d2d544dab398aac9e8266d757db51c92c22ea2333b6d5d5daad",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-E081EF68-3B0E-4A5A-8CFE-8E8B47D87BAD-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| INVOICE ID | TYPE | REFERENCE | CLOUD | PERIOD | START DATE | END DATE |\n|------------|------------|-----------|------------|---------------|----------------|----------------|\n| 282029 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM |\n| 292790 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM |\n| 292809 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM |\n| 282143 | Resource | | Azure US | February 2022 | 2/1/22, 12:00 AM | 2/28/22, 11:59 PM |"
-}
diff --git a/corpus/.vision-cache/c53e999ad6b6f8b6fd75afb9404cd098e4c96fe91a5d13fec626220c22994194.json b/corpus/.vision-cache/c53e999ad6b6f8b6fd75afb9404cd098e4c96fe91a5d13fec626220c22994194.json
deleted file mode 100644
index 3d3400a..0000000
--- a/corpus/.vision-cache/c53e999ad6b6f8b6fd75afb9404cd098e4c96fe91a5d13fec626220c22994194.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "c53e999ad6b6f8b6fd75afb9404cd098e4c96fe91a5d13fec626220c22994194",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-01147D13-F369-4441-B97D-9354DA79DF93-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Type | User | Date Range |\n|---------------------|----------------|------------------|\n| All Types | Users | All Dates |\n\n### RECENT ACTIVITY REPORT\n\n- **Admin - kulkarni** \n - User created with roles 'System Admin'. \n - Date: 01/19/2026 08:27 PM \n - Author: alex \n\n- **Backup - ThuanTestRHEL01-migrated** \n - New backup has successfully been created for 'Jabalabs'. \n - Date: 12/19/2025 01:40 AM \n - Author: ttran \n\n- **Provisioning - Jabro-Test-01** \n - New instance has successfully been created by Jabalabs. \n - Date: 12/18/2025 05:19 AM \n - Author: sean"
-}
diff --git a/corpus/.vision-cache/c8d0b1672ec076a1f5d5886a9622c098b94d6ac64eb130f3ca10f1cdfac37a4e.json b/corpus/.vision-cache/c8d0b1672ec076a1f5d5886a9622c098b94d6ac64eb130f3ca10f1cdfac37a4e.json
deleted file mode 100644
index 7c4e3b9..0000000
--- a/corpus/.vision-cache/c8d0b1672ec076a1f5d5886a9622c098b94d6ac64eb130f3ca10f1cdfac37a4e.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "c8d0b1672ec076a1f5d5886a9622c098b94d6ac64eb130f3ca10f1cdfac37a4e",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-ECB853BF-5ACC-4D03-BCC3-AF5A1D2706A3-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| LAST RESULT | TYPE | NAME | DETAILS | LAST RUN | NEXT RUN |\n|-------------|----------------|-----------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------|-------------------------|\n| \u2705 | Workflow Job | | | 11/14/2019 02:42 PM | |\n| \u2705 | Security Scan Job | Centos 8 SCAP Scan Job | | 01/23/2022 12:43 PM | |\n| \u274c | Security Scan Job | | | 04/22/2021 09:15 AM | |"
-}
diff --git a/corpus/.vision-cache/d229d8077de5254220a83ba7fe7fbba24a6d50d3e5e6c0eba0eb707bd1264f86.json b/corpus/.vision-cache/d229d8077de5254220a83ba7fe7fbba24a6d50d3e5e6c0eba0eb707bd1264f86.json
deleted file mode 100644
index 3ceb6aa..0000000
--- a/corpus/.vision-cache/d229d8077de5254220a83ba7fe7fbba24a6d50d3e5e6c0eba0eb707bd1264f86.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "d229d8077de5254220a83ba7fe7fbba24a6d50d3e5e6c0eba0eb707bd1264f86",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-1E7A4007-3C1F-4E44-A046-41A0C62111AA-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| STATUS | NAME | ADDRESS(ES) |\n|--------|------|-------------|\n| Running | qa-hosts-kube-1 | 10.x.x.x |\n| Running | qa-hosts-kube-2 | 10.x.x.x |\n| Running | qa-hosts-kube-3 | 10.x.x.x |\n| Running | qa-hosts-kube-4 | 10.x.x.x |"
-}
diff --git a/corpus/.vision-cache/d5277987d200c169f9297345c3971cd27ed731fe97f8b4f9d9667c86c3553610.json b/corpus/.vision-cache/d5277987d200c169f9297345c3971cd27ed731fe97f8b4f9d9667c86c3553610.json
deleted file mode 100644
index c74452e..0000000
--- a/corpus/.vision-cache/d5277987d200c169f9297345c3971cd27ed731fe97f8b4f9d9667c86c3553610.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "d5277987d200c169f9297345c3971cd27ed731fe97f8b4f9d9667c86c3553610",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-5E19B144-131B-4F0D-892B-9D10DB431658-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| YEAR | 2020 | 2021 | 2022 |\n|------|------|------|------|\n| YEAR | 10000.0 | 15000.0 | 8000.0 |"
-}
diff --git a/corpus/.vision-cache/d5a971d5baea55392f51f6f77fd9c81208c6b92157fd5e483a3db302b03f9dbd.json b/corpus/.vision-cache/d5a971d5baea55392f51f6f77fd9c81208c6b92157fd5e483a3db302b03f9dbd.json
deleted file mode 100644
index 3401e99..0000000
--- a/corpus/.vision-cache/d5a971d5baea55392f51f6f77fd9c81208c6b92157fd5e483a3db302b03f9dbd.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "d5a971d5baea55392f51f6f77fd9c81208c6b92157fd5e483a3db302b03f9dbd",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-36CA0790-41CA-421C-9971-50062F8B82F4-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Category | Price | Cost |\n|----------------|----------|--------|\n| COMPUTE | $102 | $102.30|\n| MEMORY | $0 | $0 |\n| STORAGE | $12 | $12.42 |\n| NETWORK | $0.01 | $0.01 |\n| EXTRA | $0 | $0 |\n| MTD PRICE | $115 | $114.73|\n| TOTAL (PROJECTED) | $115 | $114.73|"
-}
diff --git a/corpus/.vision-cache/d9e0bfda4cf3d77ebf33a8c86b0be7672f90d9c5a471074c2f22fa74b39ac988.json b/corpus/.vision-cache/d9e0bfda4cf3d77ebf33a8c86b0be7672f90d9c5a471074c2f22fa74b39ac988.json
deleted file mode 100644
index 30780b7..0000000
--- a/corpus/.vision-cache/d9e0bfda4cf3d77ebf33a8c86b0be7672f90d9c5a471074c2f22fa74b39ac988.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "d9e0bfda4cf3d77ebf33a8c86b0be7672f90d9c5a471074c2f22fa74b39ac988",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-E455650E-5DD7-40E6-BF40-5449281F27C2-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| CLOUD | TYPE | NAME | PLAN | START DATE | END DATE | USAGE STATUS | USAGE PRICE |\n|-------|------------|-------------|---------------------------------------------------------------------|----------------------|--------------------|---------------|--------------|\n| AWS-US-EAST-2 | Discovered | bastion | T2 Medium - 2 Core, 4GB Memory | 11/10/2022 09:07 AM | Stopped | $1.4006 |\n| | | | | | | | |\n| | Price Type | Quantity | | | | | |\n| | Storage | gp2 | 35 GB | | | | |\n| AWS-US-EAST-2 | Discovered | bastion | T2 Medium - 2 Core, 4GB Memory | 11/10/2022 08:29 AM | Running | $0.0324 |\n| | | | | | | | |\n| | Price Type | Quantity | | | | | |\n| | Compute | N/A | | | | | |\n| | Storage | gp2 | 35 GB | | | $0.0293 | |\n| | | | | | | | |\n| AWS-US-EAST-2 | Discovered | bastion | T2 Medium - 2 Core, 4GB Memory | 08/27/2022 07:36 PM | Stopped | $8.5582 |\n| | | | | | | | |\n| | Price Type | Quantity | | | | | |\n| | Storage | gp2 | 35 GB | | | $8.5582 | |"
-}
diff --git a/corpus/.vision-cache/dc38b36144b0c1b3a79b915c1a19ba327b4a4b582fc7f1e96be238dfafe9a08d.json b/corpus/.vision-cache/dc38b36144b0c1b3a79b915c1a19ba327b4a4b582fc7f1e96be238dfafe9a08d.json
deleted file mode 100644
index fcf0eb7..0000000
--- a/corpus/.vision-cache/dc38b36144b0c1b3a79b915c1a19ba327b4a4b582fc7f1e96be238dfafe9a08d.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "dc38b36144b0c1b3a79b915c1a19ba327b4a4b582fc7f1e96be238dfafe9a08d",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-CDD94D4F-361B-4237-B8FD-B88CCFCB6118-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Filters | Date Run | Report Type | Created By | Status |\n|---------|---------------------|----------------------|--------------|--------|\n| Automation Analytics Feb 22, 2022 21:29:37 | 02/22/2022 02:29 PM | Automation Analytics | | Ready |\n| Automation Analytics Feb 22, 2022 21:17:59 | 02/22/2022 02:17 PM | Automation Analytics | | Ready |\n| Automation Analytics Feb 22, 2022 19:41:56 | 02/22/2022 12:41 PM | Automation Analytics | | Ready |\n| Automation Analytics Feb 22, 2022 19:28:00 | 02/22/2022 12:28 PM | Automation Analytics | | Ready |\n| Automation Analytics Feb 22, 2022 19:20:08 | 02/22/2022 12:20 PM | Automation Analytics | | Ready |\n| Automation Analytics Feb 22, 2022 17:49:16 | 02/22/2022 10:49 AM | Automation Analytics | | Ready |\n| Automation Overview Feb 21, 2022 22:07:43 | 02/21/2022 03:07 PM | Automation Overview | | Ready |\n| Automation Overview Feb 21, 2022 21:35:16 | 02/21/2022 02:35 PM | Automation Overview | | Ready |\n| Automation Overview Feb 21, 2022 21:31:53 | 02/21/2022 02:31 PM | Automation Overview | | Ready |"
-}
diff --git a/corpus/.vision-cache/e3ae83786639dd50cce28dffaf6ab86d1998bacaf1e06039eda1592a9b3bcb1b.json b/corpus/.vision-cache/e3ae83786639dd50cce28dffaf6ab86d1998bacaf1e06039eda1592a9b3bcb1b.json
deleted file mode 100644
index ed082c5..0000000
--- a/corpus/.vision-cache/e3ae83786639dd50cce28dffaf6ab86d1998bacaf1e06039eda1592a9b3bcb1b.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "e3ae83786639dd50cce28dffaf6ab86d1998bacaf1e06039eda1592a9b3bcb1b",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-88431DCD-48BE-4414-BC59-89F31565FE07-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| NAME | REGION | TERM | CURRENT COST | QUANTITY | PROPOSED COST | SAVINGS |\n|------------|---------|---------|--------------|----------|---------------|-------------|\n| Standard_D2 | westus | P1Y | $109.63 | 1 | $75.23 | $34.40 |"
-}
diff --git a/corpus/.vision-cache/e63485cb67e53e7abed466429e684178cb1963a618bce5c0411158a398b5807c.json b/corpus/.vision-cache/e63485cb67e53e7abed466429e684178cb1963a618bce5c0411158a398b5807c.json
deleted file mode 100644
index 7498c52..0000000
--- a/corpus/.vision-cache/e63485cb67e53e7abed466429e684178cb1963a618bce5c0411158a398b5807c.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "e63485cb67e53e7abed466429e684178cb1963a618bce5c0411158a398b5807c",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-EA3645F4-5E49-4CFC-90CF-4A04880BF602-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Month | Budget | Actual |\n|-------|---------|--------|\n| January | $25,000 | $17,634 |\n| February | $25,000 | $25,149 |\n| March | $25,000 | $27,313 |\n| April | $25,000 | $30,827 |\n| May | $25,000 | $34,149 |\n| June | $25,000 | $33,066 |\n| July | $25,000 | $19,850 |\n| August | $25,000 | $19,509 |\n| September | $25,000 | $34,380 |\n| October | $25,000 | $30,328 |\n| November | $25,000 | $20,517 |\n| December | $25,000 | $17,226 |"
-}
diff --git a/corpus/.vision-cache/ef8ff91132425a90d6d32ce373fcd30daff9d6ffc979e37edd4937978945e83a.json b/corpus/.vision-cache/ef8ff91132425a90d6d32ce373fcd30daff9d6ffc979e37edd4937978945e83a.json
deleted file mode 100644
index 414e66b..0000000
--- a/corpus/.vision-cache/ef8ff91132425a90d6d32ce373fcd30daff9d6ffc979e37edd4937978945e83a.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "ef8ff91132425a90d6d32ce373fcd30daff9d6ffc979e37edd4937978945e83a",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-70A9C315-58C0-4BF7-94E0-3F370A17D1E4-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| CLOUD | COUNT | MEMORY | STORAGE | CPU | PRICE |\n|-------|-------|--------|---------|-----|-------|\n| VMware Demo Cluster | 19 | 72.4GiB | 842.0GiB | 12 | $143.94 |\n| Nutanix Labs 2 | 7 | 52.5GiB | 720.0GiB | 8 | $91.82 |\n| AWS MorpheusDemo | 5 | 7.0GiB | 60.0GiB | 1 | $17.41 |\n| Other Instance 1 | 1 | 7.5GiB | 90.0GiB | 4 | $15.08 |\n| Other Instance 2 | 1 | 2.0GiB | 30.0GiB | 1 | $0.00 |\n| Other Instance 3 | 1 | 2.0GiB | 10.0GiB | 1 | $0.00 |\n| Other Instance 4 | 1 | 8.0GiB | 120.0GiB | 1 | $26.23 |\n| Other Instance 5 | 1 | 16.0GiB | 160.0GiB | 1 | $51.78 |"
-}
diff --git a/corpus/.vision-cache/f2dfebdda3640d24c45ccb19f3826bc33b86165da977a9d031143b8f2bde7fa2.json b/corpus/.vision-cache/f2dfebdda3640d24c45ccb19f3826bc33b86165da977a9d031143b8f2bde7fa2.json
deleted file mode 100644
index a17b39e..0000000
--- a/corpus/.vision-cache/f2dfebdda3640d24c45ccb19f3826bc33b86165da977a9d031143b8f2bde7fa2.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "f2dfebdda3640d24c45ccb19f3826bc33b86165da977a9d031143b8f2bde7fa2",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-A7B59327-4830-4BD7-9653-DBC1F89E3304-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| NAME | CODE |\n| --- | --- |\n| Cloud Resources | cr |"
-}
diff --git a/corpus/.vision-cache/f4c3c36ba08c51a68c2a73ec1a74884db0e83d367b9e8a5e01206c7700343fe8.json b/corpus/.vision-cache/f4c3c36ba08c51a68c2a73ec1a74884db0e83d367b9e8a5e01206c7700343fe8.json
deleted file mode 100644
index 51459ee..0000000
--- a/corpus/.vision-cache/f4c3c36ba08c51a68c2a73ec1a74884db0e83d367b9e8a5e01206c7700343fe8.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "f4c3c36ba08c51a68c2a73ec1a74884db0e83d367b9e8a5e01206c7700343fe8",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-CE0F030E-A45D-4412-92D9-38608B669FC9-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Configuration | Group: All Clouds | Environment: Dev |\n|---------------|--------------------|-------------------|\n| Cloud: QA Amazon | Resource Pool: labs | Network: 172.31.0.0/20 (subnet-22ba157b) |\n| Plan: T2 Micro - 1 Core, 1GB Memory | Name: My Workload | Price: $11.3016 / Month |"
-}
diff --git a/corpus/.vision-cache/f8f32e823a7f473c35a643a5163d09e1eaa0dcdd24cba6b84766c14e09d470c2.json b/corpus/.vision-cache/f8f32e823a7f473c35a643a5163d09e1eaa0dcdd24cba6b84766c14e09d470c2.json
deleted file mode 100644
index de93268..0000000
--- a/corpus/.vision-cache/f8f32e823a7f473c35a643a5163d09e1eaa0dcdd24cba6b84766c14e09d470c2.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "f8f32e823a7f473c35a643a5163d09e1eaa0dcdd24cba6b84766c14e09d470c2",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-429BA931-09F3-4CC2-AC8E-45B3D0167664-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| TYPE | NAME | LOCATION | REGION | MONTH TO DATE | PROJECTED TOTAL |\n|------|------|----------|--------|---------------|-----------------|\n| AWS | AWS MorpheusDemo | US West (N. Cali) | ec2.us-west-1.amazonaws.com | $2,732.60 | $4,345.97 |\n| Azure | Morpheus Azure | West US | westus | $1,030.92 | $1,742.40 |\n| Nutanix Labs 2 | Nutanix Labs 2 | - | - | $511.96 | $859.41 |"
-}
diff --git a/corpus/.vision-cache/fe0c6ab239aba9109ba605bf3930353881b4a6ca629e4567c4e068f5f3289234.json b/corpus/.vision-cache/fe0c6ab239aba9109ba605bf3930353881b4a6ca629e4567c4e068f5f3289234.json
deleted file mode 100644
index aa9c7cc..0000000
--- a/corpus/.vision-cache/fe0c6ab239aba9109ba605bf3930353881b4a6ca629e4567c4e068f5f3289234.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "fe0c6ab239aba9109ba605bf3930353881b4a6ca629e4567c4e068f5f3289234",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-B0C645F7-A738-4975-9AA9-9F5E0C581874-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| Field | Value |\n|-------------|------------------------------------------------------------------------|\n| NAME | Custom App |\n| CODE | app |\n| DESCRIPTION | (empty) |\n| CATEGORY | Web |\n| LABELS | app,aws,vmware |"
-}
diff --git a/corpus/.vision-cache/fff05f56cefda6ddcc9d70456f9e7d360e6b440132b2b4c1511a56c79680c31f.json b/corpus/.vision-cache/fff05f56cefda6ddcc9d70456f9e7d360e6b440132b2b4c1511a56c79680c31f.json
deleted file mode 100644
index 5948b03..0000000
--- a/corpus/.vision-cache/fff05f56cefda6ddcc9d70456f9e7d360e6b440132b2b4c1511a56c79680c31f.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "sha": "fff05f56cefda6ddcc9d70456f9e7d360e6b440132b2b4c1511a56c79680c31f",
- "src": "https://support.hpe.com/hpesc/public/api/document/sd00007510en_us/GUID-1B7CFE86-1657-4EF7-B515-E3D104CDB5D2-high.png",
- "model": "qwen2.5vl:7b",
- "certain": true,
- "markdown": "| GROUP WORKLOADS | CLOUD WORKLOADS | CLUSTER WORKLOADS |\n|-----------------|------------------|--------------------|\n| All Clouds | QA VMware | QA Docker Cluster |\n| Permanent | QA Docker | None |\n| QA Docker | QA Nutanix Prism | QA Kubernetes Cluster |\n| QA Kubernetes | QA Amazon | |\n| group-42574 | QA Kubernetes | |\n| group-42578 | dg vmware | |\n\n| LOG HISTORY | LOG TRENDS |\n|-------------|------------|\n| ALERT sendmsg logger failed No such file or directory errno | pam_unix sudo session session opened for user root uid by uid |\n| pam_unix sudo session session closed for user root | dd-vmw-ubuntu-1 CRON pam_unix cron session closed for user root |\n| dd-vmw-ubuntu-1 CRON pam_unix cron session opened for user root by uid |\n\n| JOB EXECUTIONS | BACKUPS | TASK EXECUTIONS |\n|----------------|---------|------------------|\n| Successful: 15 | Successful: 1 | Successful: 15 |\n| Failed: 1 | Failed: 0 | Failed: 1 |\n\n| ACTIVITY |\n|----------|\n| au-dkr-blueprint-1 - apache | New backup has successfully been created for 'Morpheus QA' |\n| au-dkr-blueprint-1 - nginx | New backup has successfully been created for 'Morpheus QA' |\n| abdelkrim | Instance has successfully been deleted by 'Morpheus QA'. |\n| abdelkrim | Server has successfully been deleted by 'Morpheus QA'. |\n| au-dkr-blueprint-1 | App has successfully been created. |"
-}
diff --git a/scrape/bundles.py b/scrape/bundles.py
index 17e663c..e96d5f3 100644
--- a/scrape/bundles.py
+++ b/scrape/bundles.py
@@ -62,6 +62,11 @@ class BundleSpec:
platform: str | None = None
language: str = "en-US"
source_url: str | None = None # overrides the default support.hpe.com URL
+ # Vision-OCR this bundle's images? Default False. Image-only data lives in
+ # only a handful of docs (the release-schedule matrix); every other image
+ # in the corpus is a product UI screenshot that OCR would just add noise
+ # for. So OCR is an explicit per-bundle opt-in, not a corpus-wide sweep.
+ ocr: bool = False
# Pinned baseline bundles. docIds confirmed by probing the portal for
@@ -101,7 +106,7 @@ BUNDLES: list[BundleSpec] = [
# the matrix text comes from the VISION_OCR pass (see scrape/vision.py).
# version=None — it spans all major streams, not one release.
BundleSpec("morpheus_release_schedule", "sf000111242en_us", "HPE Morpheus Software Release Schedule",
- None, "Release Schedule", "single"),
+ None, "Release Schedule", "single", ocr=True),
]
@@ -180,6 +185,7 @@ def discover_bundle(s: requests.Session, spec: BundleSpec) -> dict[str, Any]:
"dates": {},
"landing_page": spec.doc_id,
"source_url": spec.source_url or f"https://www.hpe.com/psnow/doc/{spec.doc_id}",
+ "ocr": spec.ocr,
}
abstract_html = _get(s, f"{API}/{spec.doc_id}", expect_json=False)
@@ -211,6 +217,7 @@ def discover_bundle(s: requests.Session, spec: BundleSpec) -> dict[str, Any]:
"dates": {"Published": meta.get("published", "")},
"landing_page": landing,
"source_url": spec.source_url or DOC_URL.format(doc_id=spec.doc_id),
+ "ocr": spec.ocr,
}
diff --git a/scrape/runner.py b/scrape/runner.py
index 247e8cc..8742a5c 100644
--- a/scrape/runner.py
+++ b/scrape/runner.py
@@ -212,7 +212,10 @@ def scrape_toc_bundle(s: requests.Session, bundle: dict, force: bool, concurrenc
page_html = fetch_toc_page(s, doc_id, entry.page_id)
if not page_html:
return False
- body_md = html_to_md(page_html, s)
+ # Only pass the session (which enables image OCR) for bundles that
+ # opt in — image-only data lives in a few docs; the rest are UI
+ # screenshots that OCR would just turn into noise.
+ body_md = html_to_md(page_html, s if bundle.get("ocr") else None)
sidecar = {
"bundle_id": slug,
"page_id": entry.page_id,
@@ -243,7 +246,7 @@ def scrape_single_bundle(s: requests.Session, bundle: dict, force: bool) -> int:
if not html:
print(f" ! {slug}: empty body", file=sys.stderr)
return 0
- body_md = html_to_md(html, s)
+ body_md = html_to_md(html, s if bundle.get("ocr") else None)
sidecar = {
"bundle_id": slug,
"page_id": doc_id,
diff --git a/scrape/vision.py b/scrape/vision.py
index e8855f3..0808bc8 100644
--- a/scrape/vision.py
+++ b/scrape/vision.py
@@ -27,13 +27,17 @@ Reliability (the whole point of this module):
table wrong does so identically every run — so every transcription also
ships with a "verify against the source image" caveat.
-Cost control (a full --force re-scrape re-touches every page weekly):
+Scope: OCR is a per-bundle opt-in (BundleSpec.ocr in scrape/bundles.py), NOT
+a corpus-wide sweep. Image-only data is rare — only the release-schedule
+matrix in this corpus; every other image is a product UI screenshot that OCR
+would just turn into a noise "table". So only allowlisted bundles reach this
+module; the runner passes no session for the rest.
+
+Cost control (secondary, now that scope is an allowlist):
- Content-hash cache in corpus/.vision-cache/ — each unique image is
- OCR'd once, ever, and the result is committed so CI reuses it. The same
- diagram shared across version bundles collapses to one OCR.
- - VISION_MAX_NEW bounds NEW OCRs per run so the first run can't balloon
- into hours; the cache fills incrementally over subsequent refreshes.
- Deferred images are logged (never silently dropped).
+ OCR'd once, ever, and the result is committed so CI reuses it.
+ - VISION_MAX_NEW still bounds NEW OCRs per run as a safety net; with the
+ allowlist it rarely binds. Deferred images are logged, never dropped.
Every failure path degrades to None — a down endpoint, a timeout, a decode
error — so the scrape never blocks on vision. Defaults target the git.jpaul.io
diff --git a/scripts/vision_report.py b/scripts/vision_report.py
new file mode 100644
index 0000000..10f4a23
--- /dev/null
+++ b/scripts/vision_report.py
@@ -0,0 +1,171 @@
+"""Build a human-inspectable report of every vision-OCR'd image.
+
+Reads corpus/.vision-cache/*.json (written by scrape/vision.py) and emits a
+self-contained HTML page that puts each SOURCE IMAGE next to its OCR
+transcription, so a human can eyeball accuracy. Uncertain transcriptions
+(the two OCR samples disagreed) sort to the top. Images are downscaled and
+inlined as data URIs so the page is fully self-contained (no external
+requests) and the original full-res image is one click away.
+
+Usage:
+ python -m scripts.vision_report # -> vision_report.html
+ python -m scripts.vision_report --out /tmp/r.html
+ python -m scripts.vision_report --no-embed # link images, don't inline (tiny file)
+"""
+from __future__ import annotations
+
+import argparse
+import base64
+import glob
+import html
+import io
+import json
+import re
+import sys
+from pathlib import Path
+
+import requests
+
+ROOT = Path(__file__).resolve().parent.parent
+CACHE_DIR = ROOT / "corpus" / ".vision-cache"
+CORPUS = ROOT / "corpus"
+UA = "morpheus-docs-mcp/0.1 (+https://git.jpaul.io/justin/morpheus-docs)"
+MAX_W = 1100 # downscale width for the inlined preview
+
+
+def _basename(url: str) -> str:
+ return re.sub(r"\?.*$", "", url.rsplit("/", 1)[-1])
+
+
+def _pages_for(basename: str) -> list[str]:
+ """Which corpus pages reference this image (by filename), as bundle/page."""
+ hits: list[str] = []
+ for md in CORPUS.glob("*/*.md"):
+ try:
+ if basename in md.read_text():
+ hits.append(f"{md.parent.name}/{md.stem}")
+ except Exception:
+ continue
+ return sorted(hits)
+
+
+def _thumb(url: str, embed: bool) -> str | None:
+ if not embed:
+ return None
+ try:
+ data = requests.get(url, headers={"User-Agent": UA}, timeout=60).content
+ from PIL import Image
+ im = Image.open(io.BytesIO(data))
+ if im.mode not in ("RGB", "L"):
+ im = im.convert("RGB")
+ if im.width > MAX_W:
+ im = im.resize((MAX_W, round(im.height * MAX_W / im.width)), Image.LANCZOS)
+ buf = io.BytesIO()
+ im.save(buf, format="JPEG", quality=82)
+ return "data:image/jpeg;base64," + base64.b64encode(buf.getvalue()).decode()
+ except Exception as e:
+ print(f" ! thumb failed for {url[:70]}: {e}", file=sys.stderr)
+ return None
+
+
+def _md_table_to_html(md: str) -> str:
+ """Render a markdown table as an HTML table; fall back to otherwise."""
+ rows = [ln for ln in md.splitlines() if ln.strip().startswith("|")]
+ if len(rows) < 2:
+ return f"{html.escape(md)}"
+ def cells(line: str) -> list[str]:
+ return [c.strip() for c in line.strip().strip("|").split("|")]
+ head = cells(rows[0])
+ body = [cells(r) for r in rows[2:]] # rows[1] is the |---| separator
+ out = [""] + [f"| {html.escape(c)} | " for c in head] + ["
"]
+ for r in body:
+ out.append("" + "".join(f"| {html.escape(c)} | " for c in r) + "
")
+ out.append("
")
+ return "".join(out)
+
+
+def build(embed: bool) -> str:
+ entries = []
+ for f in sorted(glob.glob(str(CACHE_DIR / "*.json"))):
+ try:
+ entries.append(json.load(open(f)))
+ except Exception:
+ continue
+ withmd = [e for e in entries if e.get("markdown")]
+ # uncertain first, then by source URL for stable ordering
+ withmd.sort(key=lambda e: (bool(e.get("certain")), e.get("src", "")))
+
+ n_uncertain = sum(1 for e in withmd if not e.get("certain"))
+ cards = []
+ for i, e in enumerate(withmd, 1):
+ src = e.get("src", "")
+ bn = _basename(src)
+ pages = _pages_for(bn)
+ thumb = _thumb(src, embed)
+ badge = ("certain" if e.get("certain")
+ else "UNCERTAIN — samples disagreed")
+ img_html = (f"
" if thumb
+ else f"[not inlined — open original]
")
+ pages_html = " ".join(f"{html.escape(p)}" for p in pages) or "(none found)"
+ cards.append(f"""
+
+
+
+
{img_html}
+
{_md_table_to_html(e.get('markdown',''))}
+
Vision OCR inspection report
+ {len(withmd)} transcribed image(s) — {n_uncertain} uncertain, {len(withmd)-n_uncertain} certain.
+ Each source image (downscaled preview; click “open original” for full-res) is shown next to its OCR transcription.
+ Uncertain items are listed first.
+ {''.join(cards)}
+ """
+
+
+def main() -> int:
+ p = argparse.ArgumentParser(description="Build the vision-OCR inspection report.")
+ p.add_argument("--out", default=str(ROOT / "vision_report.html"))
+ p.add_argument("--no-embed", action="store_true", help="link images instead of inlining them")
+ args = p.parse_args()
+ if not CACHE_DIR.exists():
+ print(f"no cache dir at {CACHE_DIR} — run the scraper with VISION_OCR=1 first", file=sys.stderr)
+ return 1
+ html_doc = build(embed=not args.no_embed)
+ Path(args.out).write_text(html_doc)
+ print(f"wrote {args.out}", file=sys.stderr)
+ return 0
+
+
+if __name__ == "__main__":
+ sys.exit(main())