[Auto Import] Improve log format recognition #196228
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ilyannn
added
bug
ilyannn
changed the title
ilyannn
changed the title
|
Pinging @elastic/security-scalability (Team:Security-Scalability) |
…n/kibana into auto-import/csv-over-unstructured
ilyannn
changed the title
2 tasks
bhapas
reviewed
Oct 15, 2024
x-pack/plugins/integration_assistant/server/graphs/log_type_detection/detection.ts
Show resolved
Hide resolved
x-pack/plugins/integration_assistant/server/graphs/log_type_detection/prompts.ts
Outdated
Show resolved
Hide resolved
|
|
…tection/prompts.ts Co-authored-by: Bharat Pasupula <[email protected]>
I considered this, but it's mostly needed for CSV and we already have the release note about the CSV format support which kind of covers this one. |
💛 Build succeeded, but was flaky
Failed CI StepsTest Failures
Metrics [docs]
|
|
Starting backport for target branches: 8.x |
kibanamachine
pushed a commit
to kibanamachine/kibana
that referenced
this pull request
Oct 15, 2024
Previously the LLM would often select `unstructured` format for what (to our eye) clearly are CSV samples. We add the missing line break between the log samples (which should help format recognition in general) and change the prompt to clarify when the comma-separated list should be treated as a `csv` and when as `structured` format. See GitHub for examples. --------- Co-authored-by: Bharat Pasupula <[email protected]> (cherry picked from commit bdc9ce9)
💚 All backports created successfully
Note: Successful backport PRs will be merged automatically after passing CI. Questions ?Please refer to the Backport tool documentation |
kibanamachine
added a commit
that referenced
this pull request
Oct 15, 2024
# Backport This will backport the following commits from `main` to `8.x`: - [[Auto Import] Improve log format recognition (#196228)](#196228) <!--- Backport version: 9.4.3 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sqren/backport) <!--BACKPORT [{"author":{"name":"Ilya Nikokoshev","email":"[email protected]"},"sourceCommit":{"committedDate":"2024-10-15T12:02:00Z","message":"[Auto Import] Improve log format recognition (#196228)\n\nPreviously the LLM would often select `unstructured` format for what (to\r\nour eye) clearly are CSV samples.\r\n\r\nWe add the missing line break between the log samples (which should help\r\nformat recognition in general) and change the prompt to clarify when the\r\ncomma-separated list should be treated as a `csv` and when as\r\n`structured` format.\r\n\r\nSee GitHub for examples.\r\n\r\n---------\r\n\r\nCo-authored-by: Bharat Pasupula <[email protected]>","sha":"bdc9ce932bbfa606dd1f1e188c8b32df4327a0a4","branchLabelMapping":{"^v9.0.0$":"main","^v8.16.0$":"8.x","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["bug","release_note:skip","backport missing","v9.0.0","backport:prev-minor","Team:Security-Scalability","Feature:AutomaticImport"],"title":"[Auto Import] Improve log format recognition","number":196228,"url":"https://github.com/elastic/kibana/pull/196228","mergeCommit":{"message":"[Auto Import] Improve log format recognition (#196228)\n\nPreviously the LLM would often select `unstructured` format for what (to\r\nour eye) clearly are CSV samples.\r\n\r\nWe add the missing line break between the log samples (which should help\r\nformat recognition in general) and change the prompt to clarify when the\r\ncomma-separated list should be treated as a `csv` and when as\r\n`structured` format.\r\n\r\nSee GitHub for examples.\r\n\r\n---------\r\n\r\nCo-authored-by: Bharat Pasupula <[email protected]>","sha":"bdc9ce932bbfa606dd1f1e188c8b32df4327a0a4"}},"sourceBranch":"main","suggestedTargetBranches":[],"targetPullRequestStates":[{"branch":"main","label":"v9.0.0","branchLabelMappingKey":"^v9.0.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/196228","number":196228,"mergeCommit":{"message":"[Auto Import] Improve log format recognition (#196228)\n\nPreviously the LLM would often select `unstructured` format for what (to\r\nour eye) clearly are CSV samples.\r\n\r\nWe add the missing line break between the log samples (which should help\r\nformat recognition in general) and change the prompt to clarify when the\r\ncomma-separated list should be treated as a `csv` and when as\r\n`structured` format.\r\n\r\nSee GitHub for examples.\r\n\r\n---------\r\n\r\nCo-authored-by: Bharat Pasupula <[email protected]>","sha":"bdc9ce932bbfa606dd1f1e188c8b32df4327a0a4"}}]}] BACKPORT--> Co-authored-by: Ilya Nikokoshev <[email protected]>
kibanamachine
added
v8.16.0
and removed
backport missing
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Context
Previously the LLM would often select
unstructuredformat for what (to our eye) clearly are CSV samples, e.g. for this PAN-OS integration log (note the 5 samples are squashed to one line):Summary
We add the missing line break between the log samples (which should help format recognition in general) and change the prompt to clarify when the comma-separated list should be treated as a
csvand when asstructuredformat.Testing
The result is (compare to the existing integration):
{ "name": "csv", "header": false, "columns": [ "version", "timestamp", "serial_number", "log_type", "log_subtype", "session_id", "generate_time", "source_ip", "destination_ip", "nat_source_ip", "nat_destination_ip", "rule_name", "user", "", "application", "vsys", "source_zone", "destination_zone", "ingress_interface", "egress_interface", "log_forwarding_profile", "session_start_time", "elapsed_time", "repeat_count", "source_port", "destination_port", "nat_source_port", "nat_destination_port", "flags", "protocol", "action", "bytes", "bytes_sent", "bytes_received", "packets", "start_time", "elapsed_time", "category", "", "sequence_number", "", "source_location", "destination_location", "", "packets_sent", "packets_received", "session_end_reason", "", "", "", "", "", "device_name", "action_source", "", "", "", "", "", "", "", "", "", "", "", "", "timestamp_iso" ] }Generated integration: ai_panw_traffic_202410150239-1.0.0.zip
(check the sample event)
{ "ai_panw_traffic_202410150239": { "log": { "action_source": "from-policy", "category": "any", "column41": "0x0", "column48": "0", "column49": "0", "column50": "0", "column51": "0", "column55": " ", "column78": " , , , , , , , ,,,,2021-10-26T14:58:43.066-07:00", "destination_zone": "LAN", "egress_interface": "ethernet1/2", "elapsed_time": "15877", "elapsed_time_2": "0", "flags": "0x10005e", "generate_time": "2021/10/26 14:58:43", "ingress_interface": "ethernet1/2", "log_forwarding_profile": "LFPpan", "log_subtype": "end", "log_type": "TRAFFIC", "repeat_count": "1", "session_end_reason": "aged-out", "session_id": "2561", "session_start_time": "2021/10/26 14:58:43", "source_location": "United States", "source_zone": "LAN", "start_time": "2021/10/26 14:58:07", "timestamp": "2021/10/26 14:58:43", "version": "1", "vsys": "vsys1" } }, "destination": { "bytes": "1180", "geo": { "city_name": "London", "continent_name": "Europe", "country_iso_code": "GB", "country_name": "United Kingdom", "location": { "lat": 51.5142, "lon": -0.0931 }, "region_iso_code": "GB-ENG", "region_name": "England" }, "ip": "81.2.69.145", "nat": { "port": "0" }, "packets": "2", "port": "30514" }, "ecs": { "version": "8.11.0" }, "event": { "action": "allow", "category": [ "network" ], "end": "2021-10-26T14:58:43.000Z", "original": "1,2021/10/26 14:58:43,,TRAFFIC,end,2561,2021/10/26 14:58:43,81.2.69.144,81.2.69.145,,,intrazone-default,,,syslog,vsys1,LAN,LAN,ethernet1/2,ethernet1/2,LFPpan,2021/10/26 14:58:43,15877,1,57681,30514,0,0,0x10005e,udp,allow,2545,1365,1180,4,2021/10/26 14:58:07,0,any,,7022390495259151779,0x0,United States,United States,,2,2,aged-out,0,0,0,0,,PA-VM,from-policy,\" \", , , , , , , , , , , , , , , , , , , ,,,,2021-10-26T14:58:43.066-07:00", "sequence": 7022390495259151779, "start": "2021-10-26T14:58:43.000Z", "type": [ "allowed", "connection", "end" ] }, "network": { "application": "syslog", "bytes": 2545, "packets": "4", "transport": "udp" }, "observer": { "hostname": "PA-VM" }, "related": { "host": [ "PA-VM" ], "ip": [ "81.2.69.144", "81.2.69.145" ] }, "rule": { "name": "intrazone-default" }, "source": { "bytes": 1365, "geo": { "city_name": "London", "continent_name": "Europe", "country_iso_code": "GB", "country_name": "United Kingdom", "location": { "lat": 51.5142, "lon": -0.0931 }, "region_iso_code": "GB-ENG", "region_name": "England" }, "ip": "81.2.69.144", "nat": { "port": "0" }, "packets": "2", "port": "57681" }, "tags": [ "preserve_original_event" ] },