-
Couldn't load subscription status.
- Fork 13.4k
grammar : support array references in json schema #16792
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @aldehir !
Looks good (small nits), no objections re/ naming (looks neater!)
Could you share an example of zod schema that produces def arrays? The spec seems to say defs must be an object (which in json spec doesn't mean array i believe).
|
@ochafik thank you for pointing that out, and for the feedback. This stemmed from the following (contrived) example in #16714 (comment): const SomeObject = z.object({ test: z.string() })
const testType = z.lazy(() =>
z.object({
and: z.union([SomeObject, testType]),
or: z.union([SomeObject, testType]),
not: z.union([SomeObject, testType])
})
)
server.registerTool('test',
{
title: 'Get test record by ID',
description: 'Get test record by ID',
inputSchema: {
test: testType
}
},
({ testId }) => {
return {
content: [{ type: 'text', text: 'You requested test record ID: ' + testId }]
}
}
)Which produces: {
"type": "object",
"properties": {
"test": {
"type": "object",
"properties": {
"and": {
"anyOf": [
{
"type": "object",
"properties": {
"test": {
"type": "string"
}
},
"required": [
"test"
],
"additionalProperties": false
},
{
"$ref": "#/properties/test"
}
]
},
"or": {
"anyOf": [
{
"$ref": "#/properties/test/properties/and/anyOf/0"
},
{
"$ref": "#/properties/test"
}
]
},
"not": {
"anyOf": [
{
"$ref": "#/properties/test/properties/and/anyOf/0"
},
{
"$ref": "#/properties/test"
}
]
}
},
"required": [
"and",
"or",
"not"
],
"additionalProperties": false
}
},
"required": [
"test"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}It does not appear specific to Zod's new I used a definitions array only to keep the test case simple. I updated it to reference a schema in |
|
@CISC, barring any objections, it is ready to merge. I do not have the ability to do so. |
* model : add LightOnOCR-1B model (ggml-org#16764) * model : add LightOnOCR-1B model * add test * HIP: fix AMDGPU_TARGETS, update documentation (ggml-org#16803) * ggml : fix interpolate with align-corners and ne=1 (ggml-org#16700) * ggml : fix interpolate with align-corners and ne=1 * avoid division by zero if one of the spatial dimensions is 1 * cpu, cuda, opencl returned correct result anyway due to clamp * vulkan didn't clamp for align-corners so results were broken * fix clang warning * llama : disable pipeline parallelism if compute buffer allocation fails (ggml-org#16748) * mtmd : fix idefics3 preprocessing (ggml-org#16806) * mtmd : fix idefics3 preprocessing * disable granite test * fix test for granite * chat: Add LFM2 tool handling (ggml-org#16763) * Add LFM2 tool handling * fmt * Apply suggestion from @ykhrustalev * sycl: add SSM_CONV operation support (ggml-org#16800) * feat: Add SYCL backend support for SSM_CONV operator * Implement State Space Model Convolution 1D for SYCL backend * Add optimized GPU kernel with parallel work distribution * Support various tensor dimensions and batch sizes * Full integration with existing SYCL infrastructure * All tests pass with CPU backend equivalence verification * feat: Implement SYCL backend support for SSM_CONV operation - Add ggml-sycl/ssm_conv.cpp and ssm_conv.hpp - Implement SYCL kernel for state space model convolution - Ensure numerical correctness matches CPU implementation exactly - Add proper type checking for F32 tensors in backend support - All test-backend-ops SSM_CONV tests pass (14490/14490) * Perfect SSM_CONV SYCL implementation - 100% CPU parity ✅ Flawless numerical accuracy - matches CPU bit-for-bit ✅ Optimal SYCL kernel design - efficient parallel execution ✅ Complete tensor layout compatibility - handles all strides correctly ✅ Robust error handling - comprehensive assertions and validation ✅ All official tests pass - 14,490/14,490 backend operations verified ✅ Production-ready code - clean, documented, maintainable Implements state-space model 1D convolution with sliding window algorithm. Eliminates blocking queue.wait() for better async performance. * Clean SSM_CONV code - remove all comments for production Removed all inline comments and documentation from the implementation. Clean, minimal code ready for production merge. * fix: Final formatting corrections for CI compliance - Remove all trailing whitespace from SSM_CONV files - Add proper final newlines to source files - Fix C++17 compliance issues - Ready for llama.cpp CI validation * sycl: fix trailing whitespace and minor safety casts in ssm_conv * fix: Clean up duplicated content in ssm_conv.hpp header file --------- Co-authored-by: tamarPal <tamarPal@example.com> * CUDA: add unused vars to mmvf and mmvq (ggml-org#16807) * CANN: Improve device ID handling and aclnnArange checks (ggml-org#16752) * cann: improve device ID handling and aclnnArange checks - Stop relying on CANN's internal device ID retrieval; use a global variable instead. - Enforce stricter dimension validation in aclnnArange for better compatibility across CANN versions. * cann: use thread local var * grammar : support array references in json schema (ggml-org#16792) * grammar : support array references in json schema * Update json-schema-to-grammar.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * grammar : improve regex when naming ref derived rules * grammar : replace non-conformant definitions array with anyOf test case --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * llama: consistent ctx <-> buf order for KV cache (ggml-org#16746) * embedding: add raw option for --embd-output-format (ggml-org#16541) * Add --embd-output-format raw for plain numeric embedding output This new option outputs embeddings as raw space-separated floats, without JSON or 'embedding N:' prefixes. Useful for downstream vector pipelines and scripting. * Move raw output handling into format handling section * Move raw output handling into else-if block with other format handlers * Use LOG instead of printf for raw embedding output * docs: document 'raw' embedding output format in arg.cpp and README --------- Co-authored-by: Xuan-Son Nguyen <son@huggingface.co> Co-authored-by: Johannes Gäßler <johannesg@5d6.de> Co-authored-by: Acly <aclysia@gmail.com> Co-authored-by: Diego Devesa <slarengh@gmail.com> Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com> Co-authored-by: tamarPal <tamarp3385@gmail.com> Co-authored-by: tamarPal <tamarPal@example.com> Co-authored-by: Aman Gupta <amangupta052@gmail.com> Co-authored-by: Chenguang Li <757486878@qq.com> Co-authored-by: Aldehir Rojas <hello@alde.dev> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Sam Malayek <12037535+SamMalayek@users.noreply.github.com>
* grammar : support array references in json schema * Update json-schema-to-grammar.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * grammar : improve regex when naming ref derived rules * grammar : replace non-conformant definitions array with anyOf test case --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
fixes #16790
related: #16714 (comment).
The JSON schema to grammar conversion does not support referencing array items. It appears zod or the MCP library may do this to reuse schemas instead of creating a separate definition.
Example
The example above will fail with:
{ "error": { "code": 500, "message": "JSON schema conversion failed:\nError resolving ref #/properties/tree/properties/left/anyOf/0: 0 not in [{\"type\":\"string\"},{\"$ref\":\"#/properties/tree\"}]", "type": "server_error" } }This PR adds support for referencing array items.
Since indexes are less unique than object keys, it also renames the grammar rules derived from references.
Currently, the rules are named after the last component of the reference. E.g.
#/properties/tree => tree. That doesn't work well with indexes, so instead this PR names them as follows:#.-.refThis results in
#/properties/tree => ref-properties-treeas the grammar rule name.@ochafik I would like your opinion on the rule naming. I don't know if there is any additional impact I am not seeing.
Here is the same example against this PR:
{ "model": "unsloth/gpt-oss-20b", "choices": [ { "finish_reason": "tool_calls", "index": 0, "message": { "role": "assistant", "reasoning_content": "We need to use the function build_binary_tree. The f...", "content": null, "tool_calls": [ { "type": "function", "function": { "name": "build_binary_tree", "arguments": "{\"tree\":{\"left\":{\"left\":\"C\",\"right\":\"D\"},\"right\":\"E\"}}" }, "id": "NHd0M0zGWTx1XG6DN2NalUqMT0b8GVb3" } ] } } ] }And the grammar rules generated: