Introduce v3 schema version to support new knowledge format #38
Assignees
Milestone
Comments
27 tasks
russellb
added a commit
to russellb/instructlab-schema
that referenced
this issue
Jul 17, 2024
Closes instructlab#38 v3 includes some backwards incompatible changes to the knowledge schema format. Here is a diff against v2. The changes are: - Q&A pairs now have an associated context blob from the knowledge document. - There is new "document_outline" field. ```diff --- src/instructlab/schema/v2/knowledge.json 2024-07-17 12:56:37 +++ src/instructlab/schema/v3/knowledge.json 2024-07-17 13:14:56 @@ -8,7 +8,8 @@ "domain", "task_description", "seed_examples", - "document" + "document", + "document_outline" ], "unevaluatedProperties": false, "properties": { @@ -44,20 +45,37 @@ "items": { "type": "object", "required": [ - "question", - "answer" + "context", + "questions_and_answers" ], "unevaluatedProperties": false, "properties": { - "question": { - "description": "A question used for synthetic data generation.", + "context": { + "description": "A context used for synthetic data generation.", "type": "string", "minLength": 1 }, - "answer": { - "description": "The desired response for the question.", - "type": "string", - "minLength": 1 + "questions_and_answers": { + "type": "array", + "items": { + "type": "object", + "required": [ + "question", + "answer" + ], + "properties": { + "question": { + "description": "A question used for synthetic data generation.", + "type": "string", + "minLength": 1 + }, + "answer": { + "description": "The desired response for the question.", + "type": "string", + "minLength": 1 + } + } + } } } } @@ -104,6 +122,11 @@ } } } + }, + "document_outline": { + "description": "An outline of the document.", + "type": "string", + "minLength": 1 } } } ``` Signed-off-by: Russell Bryant <[email protected]>
Merged
russellb
added a commit
to russellb/instructlab-schema
that referenced
this issue
Jul 17, 2024
Closes instructlab#38 v3 includes some backwards incompatible changes to the knowledge schema format. Here is a diff against v2. The changes are: - Q&A pairs now have an associated context blob from the knowledge document. - There is new "document_outline" field. ```diff --- src/instructlab/schema/v2/knowledge.json 2024-07-17 12:56:37 +++ src/instructlab/schema/v3/knowledge.json 2024-07-17 13:14:56 @@ -8,7 +8,8 @@ "domain", "task_description", "seed_examples", - "document" + "document", + "document_outline" ], "unevaluatedProperties": false, "properties": { @@ -44,20 +45,37 @@ "items": { "type": "object", "required": [ - "question", - "answer" + "context", + "questions_and_answers" ], "unevaluatedProperties": false, "properties": { - "question": { - "description": "A question used for synthetic data generation.", + "context": { + "description": "A context used for synthetic data generation.", "type": "string", "minLength": 1 }, - "answer": { - "description": "The desired response for the question.", - "type": "string", - "minLength": 1 + "questions_and_answers": { + "type": "array", + "minItems": 3, + "uniqueItems": true, + "items": { + "type": "object", + "required": [ + "question", + "answer" + ], + "properties": { + "question": { + "description": "A question used for synthetic data generation.", + "type": "string", + "minLength": 1 + }, + "answer": { + "description": "The desired response for the question.", + "type": "string", + "minLength": 1 + } + } + } } } } @@ -104,6 +122,11 @@ } } } + }, + "document_outline": { + "description": "An outline of the document.", + "type": "string", + "minLength": 1 } } } ``` Signed-off-by: Russell Bryant <[email protected]>
russellb
added a commit
to russellb/instructlab-schema
that referenced
this issue
Jul 17, 2024
Closes instructlab#38 v3 includes some backwards incompatible changes to the knowledge schema format. Here is a diff against v2. The changes are: - Q&A pairs now have an associated context blob from the knowledge document. - There is new "document_outline" field. ```diff --- src/instructlab/schema/v2/knowledge.json 2024-07-17 12:56:37 +++ src/instructlab/schema/v3/knowledge.json 2024-07-17 13:14:56 @@ -8,7 +8,8 @@ "domain", "task_description", "seed_examples", - "document" + "document", + "document_outline" ], "unevaluatedProperties": false, "properties": { @@ -44,20 +45,37 @@ "items": { "type": "object", "required": [ - "question", - "answer" + "context", + "questions_and_answers" ], "unevaluatedProperties": false, "properties": { - "question": { - "description": "A question used for synthetic data generation.", + "context": { + "description": "A context used for synthetic data generation.", "type": "string", "minLength": 1 }, - "answer": { - "description": "The desired response for the question.", - "type": "string", - "minLength": 1 + "questions_and_answers": { + "type": "array", + "minItems": 3, + "uniqueItems": true, + "items": { + "type": "object", + "required": [ + "question", + "answer" + ], + "properties": { + "question": { + "description": "A question used for synthetic data generation.", + "type": "string", + "minLength": 1 + }, + "answer": { + "description": "The desired response for the question.", + "type": "string", + "minLength": 1 + } + } + } } } } @@ -104,6 +122,11 @@ } } } + }, + "document_outline": { + "description": "An outline of the document.", + "type": "string", + "minLength": 1 } } } ``` Signed-off-by: Russell Bryant <[email protected]>
russellb
added a commit
to russellb/instructlab-schema
that referenced
this issue
Jul 17, 2024
Closes instructlab#38 v3 includes some backwards incompatible changes to the knowledge schema format. Here is a diff against v2. The changes are: - Q&A pairs now have an associated context blob from the knowledge document. - There is new `document_outline` field. - drop `task_description` ```diff --- src/instructlab/schema/v2/knowledge.json 2024-07-17 12:56:37 +++ src/instructlab/schema/v3/knowledge.json 2024-07-17 15:38:30 @@ -6,9 +6,9 @@ "required": [ "created_by", "domain", - "task_description", "seed_examples", - "document" + "document", + "document_outline" ], "unevaluatedProperties": false, "properties": { @@ -27,15 +27,6 @@ "Pop culture" ] }, - "task_description": { - "description": "A description of the task which is used in prompts to the teacher model during synthetic data generation. The description should be detailed and prescriptive to improve the teacher model's responses.", - "type": "string", - "minLength": 1, - "examples": [ - "To teach a language model about softball history", - "To teach a language model about tabby cats" - ] - }, "seed_examples": { "description": "An array of seed examples for synthetic data generation.", "type": "array", @@ -44,20 +35,39 @@ "items": { "type": "object", "required": [ - "question", - "answer" + "context", + "questions_and_answers" ], "unevaluatedProperties": false, "properties": { - "question": { - "description": "A question used for synthetic data generation.", + "context": { + "description": "Context from the document associated with this set of sample q&a pairs.", "type": "string", "minLength": 1 }, - "answer": { - "description": "The desired response for the question.", - "type": "string", - "minLength": 1 + "questions_and_answers": { + "type": "array", + "minItems": 3, + "uniqueItems": true, + "items": { + "type": "object", + "required": [ + "question", + "answer" + ], + "properties": { + "question": { + "description": "A question used for synthetic data generation.", + "type": "string", + "minLength": 1 + }, + "answer": { + "description": "The desired response for the question.", + "type": "string", + "minLength": 1 + } + } + } } } } @@ -104,6 +114,11 @@ } } } + }, + "document_outline": { + "description": "An outline of the document.", + "type": "string", + "minLength": 1 } } } ``` Signed-off-by: Russell Bryant <[email protected]>
russellb
added a commit
to russellb/instructlab-schema
that referenced
this issue
Jul 17, 2024
Closes instructlab#38 v3 includes some backwards incompatible changes to the knowledge schema format. Here is a diff against v2. The changes are: - Q&A pairs now have an associated context blob from the knowledge document. - There is new `document_outline` field. - drop `task_description` ```diff --- src/instructlab/schema/v2/knowledge.json 2024-07-17 12:56:37 +++ src/instructlab/schema/v3/knowledge.json 2024-07-17 15:38:30 @@ -6,9 +6,9 @@ "required": [ "created_by", "domain", - "task_description", "seed_examples", - "document" + "document", + "document_outline" ], "unevaluatedProperties": false, "properties": { @@ -27,15 +27,6 @@ "Pop culture" ] }, - "task_description": { - "description": "A description of the task which is used in prompts to the teacher model during synthetic data generation. The description should be detailed and prescriptive to improve the teacher model's responses.", - "type": "string", - "minLength": 1, - "examples": [ - "To teach a language model about softball history", - "To teach a language model about tabby cats" - ] - }, "seed_examples": { "description": "An array of seed examples for synthetic data generation.", "type": "array", @@ -44,20 +35,39 @@ "items": { "type": "object", "required": [ - "question", - "answer" + "context", + "questions_and_answers" ], "unevaluatedProperties": false, "properties": { - "question": { - "description": "A question used for synthetic data generation.", + "context": { + "description": "Context from the document associated with this set of sample q&a pairs.", "type": "string", "minLength": 1 }, - "answer": { - "description": "The desired response for the question.", - "type": "string", - "minLength": 1 + "questions_and_answers": { + "type": "array", + "minItems": 3, + "uniqueItems": true, + "items": { + "type": "object", + "required": [ + "question", + "answer" + ], + "properties": { + "question": { + "description": "A question used for synthetic data generation.", + "type": "string", + "minLength": 1 + }, + "answer": { + "description": "The desired response for the question.", + "type": "string", + "minLength": 1 + } + } + } } } } @@ -104,6 +114,11 @@ } } } + }, + "document_outline": { + "description": "An outline of the document.", + "type": "string", + "minLength": 1 } } } ``` Signed-off-by: Russell Bryant <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is part of: instructlab/sdg#160
This is an example of the new format: https://github.com/instructlab/taxonomy/blob/7729fcd62ca68e36225a98a954e702734cc09ae1/knowledge/science/anatomy/tonsils/qna.yaml
The key changes are:
document_outlinefield has been added.The text was updated successfully, but these errors were encountered: