You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Refa: knowledge_graph chunk method is deprecated (#7220)
### What problem does this PR solve?
The knowledge_graph chunk method is deprecated and should no longer be
used. #7184.
### Type of change
- [x] Refactoring
Copy file name to clipboardExpand all lines: docs/references/http_api_reference.md
+1-12Lines changed: 1 addition & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -393,7 +393,6 @@ curl --request POST \
393
393
-`"presentation"`: Presentation
394
394
-`"picture"`: Picture
395
395
-`"one"`: One
396
-
-`"knowledge_graph"`: Knowledge Graph
397
396
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
398
397
-`"email"`: Email
399
398
@@ -409,10 +408,6 @@ curl --request POST \
409
408
- If `"chunk_method"` is `"qa"`, `"manuel"`, `"paper"`, `"book"`, `"laws"`, or `"presentation"`, the `"parser_config"` object contains the following attribute:
410
409
-`"raptor"`: Raptor-specific settings. Defaults to: `{"use_raptor": false}`.
411
410
- If `"chunk_method"` is `"table"`, `"picture"`, `"one"`, or `"email"`, `"parser_config"` is an empty JSON object.
412
-
- If `"chunk_method"` is `"knowledge_graph"`, the `"parser_config"` object contains the following attributes:
413
-
-`"chunk_token_count"`: Defaults to `128`.
414
-
-`"delimiter"`: Defaults to `"\n"`.
415
-
-`"entity_types"`: Defaults to `["organization","person","location","event","time"]`
416
411
417
412
#### Response
418
413
@@ -573,8 +568,6 @@ curl --request PUT \
573
568
-`"picture"`: Picture
574
569
-`"one"`:One
575
570
-`"email"`: Email
576
-
-`"knowledge_graph"`: Knowledge Graph
577
-
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
578
571
579
572
#### Response
580
573
@@ -655,7 +648,7 @@ Success:
655
648
"id": "6e211ee0723611efa10a0242ac120007",
656
649
"language": "English",
657
650
"name": "mysql",
658
-
"chunk_method": "knowledge_graph",
651
+
"chunk_method": "naive",
659
652
"parser_config": {
660
653
"chunk_token_num": 8192,
661
654
"delimiter": "\\n",
@@ -841,10 +834,6 @@ curl --request PUT \
841
834
- If `"chunk_method"` is `"qa"`, `"manuel"`, `"paper"`, `"book"`, `"laws"`, or `"presentation"`, the `"parser_config"` object contains the following attribute:
842
835
-`"raptor"`: Raptor-specific settings. Defaults to: `{"use_raptor": false}`.
843
836
- If `"chunk_method"` is `"table"`, `"picture"`, `"one"`, or `"email"`, `"parser_config"` is an empty JSON object.
844
-
- If `"chunk_method"` is `"knowledge_graph"`, the `"parser_config"` object contains the following attributes:
845
-
-`"chunk_token_count"`: Defaults to `128`.
846
-
-`"delimiter"`: Defaults to `"\n"`.
847
-
-`"entity_types"`: Defaults to `["organization","person","location","event","time"]`
Copy file name to clipboardExpand all lines: docs/references/python_api_reference.md
-4Lines changed: 0 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -145,8 +145,6 @@ The chunking method of the dataset to create. Available options:
145
145
-`"presentation"`: Presentation
146
146
-`"picture"`: Picture
147
147
-`"one"`: One
148
-
-`"knowledge_graph"`: Knowledge Graph
149
-
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
150
148
-`"email"`: Email
151
149
152
150
##### parser_config
@@ -398,8 +396,6 @@ A dictionary representing the attributes to update, with the following keys:
398
396
-`"presentation"`: Presentation
399
397
-`"picture"`: Picture
400
398
-`"one"`: One
401
-
-`"knowledge_graph"`: Knowledge Graph
402
-
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
403
399
-`"email"`: Email
404
400
-`"parser_config"`: `dict[str, Any]` The parsing configuration for the document. Its attributes vary based on the selected `"chunk_method"`:
0 commit comments