redhop 0.1.2__tar.gz

redhop-0.1.2/Cargo.toml

@@ -0,0 +1,88 @@
+[workspace]
+resolver = "2"
+members = [
+    "crates/redhop",
+    "crates/calibration",
+    "crates/diagnostics",
+    "crates/observability",
+    "crates/orchestration",
+    "crates/pipeline",
+    "crates/benchmarks",
+    "crates/examples",
+    "crates/cli",
+]
+
+[workspace.lints.rust]
+rust_2018_idioms = { level = "warn", priority = -1 }
+unused = "warn"
+
+[workspace.lints.clippy]
+# Opinionated baseline: the standard clippy groups are warnings, enforced as
+# errors in CI (`cargo clippy -- -D warnings`). priority -1 lets the specific
+# allows below win.
+all = { level = "warn", priority = -1 }
+# Deliberately permitted: index-based loops are clearer than iterator chains in
+# numeric / parallel-array kernels (pooling, centroids, bootstrap), and this is
+# a style call, not a correctness one.
+needless_range_loop = "allow"
+
+[workspace.package]
+version = "0.1.2"
+edition = "2021"
+rust-version = "1.75"
+license = "Apache-2.0"
+authors = ["Vysakh Sreenivasan", "RedHop Contributors"]
+repository = "https://github.com/vysakh0/redhop"
+homepage = "https://github.com/vysakh0/redhop"
+description = "RedHop — a reasoning-aware retrieval & context runtime for RAG: chunk, retrieve, and allocate the document context an LLM should see, with citations and a Decision Report."
+keywords = ["rag", "retrieval", "llm", "context", "nlp"]
+categories = ["text-processing", "science"]
+
+[workspace.dependencies]
+# The single published crate. Internal workspace members (cli, calibration,
+# diagnostics, observability, orchestration, pipeline, benchmarks) depend on
+# `redhop` directly — there is no more `redhop-core` / `redhop-context` / …
+# as separate crates; those are now modules: `redhop::core`, `redhop::context`, …
+redhop               = { path = "crates/redhop" }
+# Internal (publish = false). Dev / research / orchestration code that stays
+# in the workspace but is not part of the published Rust API.
+redhop-diagnostics   = { path = "crates/diagnostics" }
+redhop-observability = { path = "crates/observability" }
+redhop-orchestration = { path = "crates/orchestration" }
+redhop-pipeline      = { path = "crates/pipeline" }
+redhop-calibration   = { path = "crates/calibration" }
+
+# Core runtime / concurrency
+tokio    = { version = "1", features = ["rt-multi-thread", "macros", "fs", "sync"] }
+rayon    = "1.10"
+futures  = "0.3"
+
+# Serialization / error handling
+serde       = { version = "1", features = ["derive"] }
+serde_json  = "1"
+anyhow      = "1"
+thiserror   = "1"
+
+# Observability
+tracing            = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
+
+# Text / tokenization
+unicode-segmentation = "1.11"
+regex                = "1.10"
+
+# Optional heavyweight backends (gated behind features in their crates)
+tantivy = "0.22"
+
+# Bench / test
+criterion = { version = "0.5", features = ["html_reports"] }
+
+[profile.release]
+lto = "thin"
+codegen-units = 1
+opt-level = 3
+debug = false
+
+[profile.bench]
+lto = "thin"
+codegen-units = 1

redhop-0.1.2/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

redhop-0.1.2/PKG-INFO

@@ -0,0 +1,140 @@
+Metadata-Version: 2.4
+Name: redhop
+Version: 0.1.2
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Rust
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+License-File: LICENSE
+Summary: Reasoning-aware context runtime for RAG — chunk, retrieve, and allocate the document context an LLM should see, with citations and a Decision Report. In-process, no vector DB.
+Keywords: rag,retrieval,llm,context,nlp
+Author: Vysakh Sreenivasan, RedHop Contributors
+License: Apache-2.0
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://github.com/vysakh0/redhop
+Project-URL: Repository, https://github.com/vysakh0/redhop
+
+# RedHop
+
+**A reasoning-aware context runtime for RAG.**
+
+Hand it a document and a question. RedHop chunks, retrieves, and allocates the
+context your model should actually see — then tells you what it kept, what it dropped,
+and why, with citations back to the source. No vector database, no LLM, all in-process.
+
+```python
+import redhop
+
+doc = redhop.Document.from_file("contract.pdf")
+ctx = doc.context("What is the governing law?")
+
+answer = llm.generate(ctx.text())   # any LLM provider — no lock-in
+```
+
+```bash
+pip install redhop
+```
+
+One self-contained wheel — no Python dependencies. The default lexical tier needs no
+model at all; the semantic/rerank tiers download a small model on first use (cached).
+
+## The idea
+
+**Retrieval quality is not the same as reasoning quality.** Transformers tolerate
+irrelevant context far better than they tolerate *missing reasoning links* — so the
+chunk a multi-hop answer depends on is often low-relevance to the query and gets
+silently pruned. RedHop's default keeps it, and makes the trade-off visible. It is
+**not** a retriever, vector database, agent framework, or workflow engine — it does one
+thing: turn a document and a query into the right prompt context, and explain the
+decision.
+
+## It explains every decision
+
+Every call returns a **Decision Report** — what it kept, what it dropped, and *why*,
+including when it deliberately leaves a small context untouched.
+
+```python
+print(ctx.report)
+```
+
+```text
+RedHop Decision Report
+══════════════════════
+
+Decision: Auto → pruning (intervened on a diluted context)
+
+  Why:
+    - large/diluted contexts dilute attention; pruning recovers signal density
+  Result:
+    - removed distractor chunks, kept all query-relevant evidence
+    - preserved a second-hop link a plain relevance filter would drop
+
+Diagnostics
+───────────
+  Chunks:             24 → 3
+  Second-hop rescues: 1
+```
+
+Read the fields directly via `ctx.report.auto_decision`, `total_tokens`,
+`retained_evidence_ratio`, or call `doc.analyze(query)` for the report **without**
+assembling a context.
+
+## Cite the evidence
+
+Every selected chunk remembers where it came from:
+
+```python
+for c in ctx.citations:
+    print(c["source"], c["page"], c["heading"])
+    # contract.pdf  3     None      ->  "contract.pdf, p.3"
+    # notes.md      None  "Refunds" ->  "notes.md -> Refunds"
+```
+
+## Loading documents
+
+| On-ramp | For |
+| --- | --- |
+| `Document.from_text(text)` | text you already have |
+| `Document.from_chunks([...])` | content you already chunked |
+| `Document.from_file("x.pdf")` | a file — PDF, DOCX, PPTX, XLSX, Markdown, or text/code |
+| `Document.from_bytes(data, source="x.pdf")` | bytes you fetched (S3 / GCS / HTTP / DB) |
+| `Document.from_folder("./docs", persist=True)` | a whole directory, with an optional incremental on-disk index |
+
+## Retrieval tiers — no vector database
+
+A ladder; start cheap, climb only when a query needs it. All in-process, no ANN, no
+index server.
+
+```python
+doc = redhop.Document.from_text(text, retrieval="lexical")   # BM25 (default)
+doc = redhop.Document.from_text(text, retrieval="hybrid",   model="bge-small")  # BM25 -> dense rerank
+doc = redhop.Document.from_text(text, retrieval="semantic", model="bge-small")  # exact cosine over all chunks
+```
+
+Add `rerank="cross-encoder"` on any tier for a precise (slower) second stage.
+
+## Assembly strategies
+
+| `strategy=` | What it does |
+| --- | --- |
+| `reasoning_preserving` *(default)* | keep query-relevant seeds **and** rescue low-relevance chunks linked to one; drop only unlinked junk |
+| `distractor_filtered` | drop everything below a query-grounding bar |
+| `max_density` | greedily pack the densest chunks into the budget |
+| `raw_topk` | keep retrieval order until the budget fills |
+| `auto` | size-gated: pass small contexts through, prune large/diluted ones |
+
+Already have chunks from your own retriever? Use `redhop.build_context(query,
+retrieved_chunks=chunks, ...)` for the low-level surface.
+
+## Documentation
+
+Full docs, the comparison vs LangChain / LlamaIndex, and the evidence behind every
+default: **https://redhop.dev**
+
+Apache-2.0. Also available for **Node.js** (`npm install redhop`) and **Rust**
+(`cargo add redhop`).
+

redhop-0.1.2/README.md

@@ -0,0 +1,119 @@
+# RedHop
+
+**A reasoning-aware context runtime for RAG.**
+
+Hand it a document and a question. RedHop chunks, retrieves, and allocates the
+context your model should actually see — then tells you what it kept, what it dropped,
+and why, with citations back to the source. No vector database, no LLM, all in-process.
+
+```python
+import redhop
+
+doc = redhop.Document.from_file("contract.pdf")
+ctx = doc.context("What is the governing law?")
+
+answer = llm.generate(ctx.text())   # any LLM provider — no lock-in
+```
+
+```bash
+pip install redhop
+```
+
+One self-contained wheel — no Python dependencies. The default lexical tier needs no
+model at all; the semantic/rerank tiers download a small model on first use (cached).
+
+## The idea
+
+**Retrieval quality is not the same as reasoning quality.** Transformers tolerate
+irrelevant context far better than they tolerate *missing reasoning links* — so the
+chunk a multi-hop answer depends on is often low-relevance to the query and gets
+silently pruned. RedHop's default keeps it, and makes the trade-off visible. It is
+**not** a retriever, vector database, agent framework, or workflow engine — it does one
+thing: turn a document and a query into the right prompt context, and explain the
+decision.
+
+## It explains every decision
+
+Every call returns a **Decision Report** — what it kept, what it dropped, and *why*,
+including when it deliberately leaves a small context untouched.
+
+```python
+print(ctx.report)
+```
+
+```text
+RedHop Decision Report
+══════════════════════
+
+Decision: Auto → pruning (intervened on a diluted context)
+
+  Why:
+    - large/diluted contexts dilute attention; pruning recovers signal density
+  Result:
+    - removed distractor chunks, kept all query-relevant evidence
+    - preserved a second-hop link a plain relevance filter would drop
+
+Diagnostics
+───────────
+  Chunks:             24 → 3
+  Second-hop rescues: 1
+```
+
+Read the fields directly via `ctx.report.auto_decision`, `total_tokens`,
+`retained_evidence_ratio`, or call `doc.analyze(query)` for the report **without**
+assembling a context.
+
+## Cite the evidence
+
+Every selected chunk remembers where it came from:
+
+```python
+for c in ctx.citations:
+    print(c["source"], c["page"], c["heading"])
+    # contract.pdf  3     None      ->  "contract.pdf, p.3"
+    # notes.md      None  "Refunds" ->  "notes.md -> Refunds"
+```
+
+## Loading documents
+
+| On-ramp | For |
+| --- | --- |
+| `Document.from_text(text)` | text you already have |
+| `Document.from_chunks([...])` | content you already chunked |
+| `Document.from_file("x.pdf")` | a file — PDF, DOCX, PPTX, XLSX, Markdown, or text/code |
+| `Document.from_bytes(data, source="x.pdf")` | bytes you fetched (S3 / GCS / HTTP / DB) |
+| `Document.from_folder("./docs", persist=True)` | a whole directory, with an optional incremental on-disk index |
+
+## Retrieval tiers — no vector database
+
+A ladder; start cheap, climb only when a query needs it. All in-process, no ANN, no
+index server.
+
+```python
+doc = redhop.Document.from_text(text, retrieval="lexical")   # BM25 (default)
+doc = redhop.Document.from_text(text, retrieval="hybrid",   model="bge-small")  # BM25 -> dense rerank
+doc = redhop.Document.from_text(text, retrieval="semantic", model="bge-small")  # exact cosine over all chunks
+```
+
+Add `rerank="cross-encoder"` on any tier for a precise (slower) second stage.
+
+## Assembly strategies
+
+| `strategy=` | What it does |
+| --- | --- |
+| `reasoning_preserving` *(default)* | keep query-relevant seeds **and** rescue low-relevance chunks linked to one; drop only unlinked junk |
+| `distractor_filtered` | drop everything below a query-grounding bar |
+| `max_density` | greedily pack the densest chunks into the budget |
+| `raw_topk` | keep retrieval order until the budget fills |
+| `auto` | size-gated: pass small contexts through, prune large/diluted ones |
+
+Already have chunks from your own retriever? Use `redhop.build_context(query,
+retrieved_chunks=chunks, ...)` for the low-level surface.
+
+## Documentation
+
+Full docs, the comparison vs LangChain / LlamaIndex, and the evidence behind every
+default: **https://redhop.dev**
+
+Apache-2.0. Also available for **Node.js** (`npm install redhop`) and **Rust**
+(`cargo add redhop`).

redhop-0.1.2/crates/redhop/Cargo.toml

@@ -0,0 +1,72 @@
+[package]
+name = "redhop"
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+repository.workspace = true
+homepage.workspace = true
+keywords.workspace = true
+categories.workspace = true
+description = "Reasoning-aware context runtime for RAG — chunk, retrieve, and allocate the document context an LLM should see, with citations and a Decision Report. No vector DB, in-process."
+# Shipped to crates.io so the package page isn't blank. Relative path from the
+# crate; cargo bundles the file into the published tarball.
+readme = "README.md"
+
+[lib]
+path = "src/lib.rs"
+
+[features]
+default = []
+# Built-in document parsers (PDF/DOCX/PPTX/XLSX + text/code/markdown) and the
+# `read_file` / `read_bytes` / `read_folder` loaders.
+files = [
+    "dep:docx-rs",
+    "dep:calamine",
+    "dep:zip",
+    "dep:quick-xml",
+    "dep:pdf-extract",
+    "dep:ignore",
+]
+# Semantic retrieval tier: bundled ONNX embedder + model registry, plus the
+# cross-encoder reranker. Shares one ONNX runtime / one tokenizers dep.
+semantic = ["dep:ort", "dep:tokenizers", "dep:hf-hub"]
+
+[dependencies]
+# ── always-on (the lexical-only build pulls only these) ──
+serde                = { workspace = true }
+serde_json           = { workspace = true }
+thiserror            = { workspace = true }
+tracing              = { workspace = true }
+unicode-segmentation = { workspace = true }
+regex                = { workspace = true }
+rayon                = { workspace = true }
+tantivy              = { workspace = true }
+tokio                = { workspace = true }
+futures              = { workspace = true }
+async-trait          = "0.1"
+parking_lot          = "0.12"
+rust-stemmers        = "1.2"
+lru                  = "0.12"
+
+# ── `files` feature (document parsers) ──
+docx-rs     = { version = "0.4", optional = true }
+calamine    = { version = "0.32", optional = true }
+zip         = { version = "2", default-features = false, features = ["deflate"], optional = true }
+quick-xml   = { version = "0.37", optional = true }
+pdf-extract = { version = "0.7", optional = true }
+ignore      = { version = "0.4", optional = true }
+
+# ── `semantic` feature (ONNX embedder + cross-encoder reranker) ──
+# `ort` is pinned exactly: the 2.x release-candidate line churns transitive
+# (ndarray) constraints between RCs. We avoid the ndarray feature entirely
+# and construct tensors from plain (shape, Vec) pairs to keep deps minimal.
+ort        = { version = "=2.0.0-rc.10", optional = true, default-features = false, features = ["std", "download-binaries"] }
+tokenizers = { version = "0.20", optional = true, default-features = false, features = ["onig"] }
+# Auto-downloads curated ONNX models by name. Sync `ureq` + `rustls-tls`
+# (no OpenSSL) for clean Linux/Windows/macOS builds.
+hf-hub     = { version = "0.5", optional = true, default-features = false, features = ["ureq", "rustls-tls"] }
+
+[lints]
+workspace = true