embedflow 0.1.0__tar.gz

embedflow-0.1.0/CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+
+## v0.1.0 — initial public release
+
+- Candidate-compatibility analysis and Mode A evaluation workflows.
+- Frozen T2-v1 finite-tail diagnostic with explicit empirical-warning language.
+- FAISS and Qdrant index adapters.
+- Persistent target-vector cache and progressive materialization queue.
+- FastAPI service, search/status/prewarm endpoints, and dashboard.
+- Latency telemetry, economics projections, report generation, and demos.
+- Public packaging, examples, tests, CI configuration, and contributor docs.
+
+This is an early open-source release. See the limitations in the README and
+`docs/concepts.md` before using it for a production migration.

embedflow-0.1.0/CITATION.cff

@@ -0,0 +1,22 @@
+cff-version: 1.2.0
+title: "EmbedFlow: Upgrading Legacy Embeddings Without Full Upfront Re-Embedding"
+message: "If EmbedFlow contributes to your work, please cite this software release."
+type: software
+version: 0.1.0
+date-released: 2026-09-06
+repository-code: "https://github.com/arnsri33/embedflow"
+url: "https://github.com/arnsri33/embedflow"
+license: Apache-2.0
+authors:
+  - family-names: "Srivastav"
+    given-names: "Arnav"
+keywords:
+  - embeddings
+  - vector search
+  - information retrieval
+  - progressive migration
+  - RAG
+abstract: >-
+  EmbedFlow analyzes whether a legacy embedding index can serve as a candidate
+  pool for a new embedding model and provides progressive target-vector
+  materialization while the new model is serving.

embedflow-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,53 @@
+# Contributing to EmbedFlow
+
+Thanks for helping make progressive embedding migration useful and rigorous.
+
+## Development setup
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+python -m pip install -e '.[dev]'
+```
+
+Optional integrations can be installed with `.[faiss]`, `.[qdrant]`,
+`.[models]`, or `.[dashboard]`.
+
+## Checks before opening a pull request
+
+```bash
+ruff check .
+pytest -q
+python -m build
+```
+
+Keep tests CPU-safe. Mark GPU-only tests explicitly and make them skip cleanly
+when CUDA or model weights are unavailable.
+
+## Adding a vector database backend
+
+Implement the `VectorIndex` contract in `embedflow/indexes/base.py`, including
+`search`, `size`, `metadata`, and persistence/connection behavior. Add the
+backend behind an explicit optional dependency, validate dimensions and metric
+semantics, document credentials through environment variables, and add an
+integration test that skips when the service is unavailable. Do not report ANN
+health as PASS unless an exact/reference comparison has actually been run.
+
+## Adding a model adapter
+
+Preserve the `EmbeddingModel` contract: query/document encoding, dimension,
+normalization, pooling, prompts, and a semantic fingerprint. Add tests for
+the fingerprint and for query/document shape and normalization behavior.
+
+## Research and reproducibility
+
+Do not modify the frozen T2-v1 implementation or its hash specification as a
+side effect of product changes. Changes to metrics or evaluation semantics
+must include a regression test and an explanation in the pull request.
+
+## Pull requests
+
+Describe the user-visible behavior, compatibility implications, test commands,
+and any limitations. Keep changes focused, avoid committing generated caches,
+model weights, private data, or credentials, and update documentation for new
+CLI flags or configuration fields.

embedflow-0.1.0/LICENSE

@@ -0,0 +1,178 @@
+Copyright 2026 Arnav Srivastav
+
+                                 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

embedflow-0.1.0/MANIFEST.in

@@ -0,0 +1,11 @@
+include README.md README_PYPI.md LICENSE CHANGELOG.md CONTRIBUTING.md SECURITY.md CITATION.cff requirements.txt requirements-dev.txt
+recursive-include docs *
+recursive-include examples *.md *.yaml *.json *.jsonl *.py
+recursive-include scripts *.sh *.py
+recursive-include frozen *.md *.sha256
+prune .github
+prune tests
+global-exclude __pycache__
+global-exclude *.py[cod]
+global-exclude *.index *.npy *.npz *.sqlite *.sqlite3 *.db
+global-exclude *.safetensors *.bin *.pt *.pth *.onnx

embedflow-0.1.0/PKG-INFO

@@ -0,0 +1,210 @@
+Metadata-Version: 2.4
+Name: embedflow
+Version: 0.1.0
+Summary: Progressive embedding-model migration over existing vector indexes.
+Author: Arnav Srivastav
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://embedflow.org
+Project-URL: Repository, https://github.com/arnsri33/embedflow
+Project-URL: Documentation, https://github.com/arnsri33/embedflow#readme
+Project-URL: Issues, https://github.com/arnsri33/embedflow/issues
+Keywords: embeddings,vector-search,rag,information-retrieval,faiss,qdrant
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: tqdm>=4.65
+Provides-Extra: faiss
+Requires-Dist: faiss-cpu>=1.8.0; extra == "faiss"
+Provides-Extra: qdrant
+Requires-Dist: qdrant-client>=1.9; extra == "qdrant"
+Provides-Extra: models
+Requires-Dist: huggingface-hub>=0.20; extra == "models"
+Requires-Dist: transformers>=4.45; extra == "models"
+Requires-Dist: sentence-transformers>=3.0; extra == "models"
+Requires-Dist: torch>=2.2; extra == "models"
+Provides-Extra: dashboard
+Requires-Dist: fastapi>=0.100; extra == "dashboard"
+Requires-Dist: uvicorn[standard]>=0.23; extra == "dashboard"
+Requires-Dist: pydantic>=2.0; extra == "dashboard"
+Provides-Extra: all
+Requires-Dist: faiss-cpu>=1.8.0; extra == "all"
+Requires-Dist: qdrant-client>=1.9; extra == "all"
+Requires-Dist: huggingface-hub>=0.20; extra == "all"
+Requires-Dist: transformers>=4.45; extra == "all"
+Requires-Dist: sentence-transformers>=3.0; extra == "all"
+Requires-Dist: torch>=2.2; extra == "all"
+Requires-Dist: fastapi>=0.100; extra == "all"
+Requires-Dist: uvicorn[standard]>=0.23; extra == "all"
+Requires-Dist: pydantic>=2.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: build>=1.2; extra == "dev"
+Dynamic: license-file
+
+# EmbedFlow
+
+**Progressive embedding-model migration over existing vector indexes.**
+
+EmbedFlow lets a new embedding model serve over candidates from an existing
+vector index while target document vectors are materialized progressively. It
+supports migration analysis, persistent caching, background work, FAISS,
+Qdrant, a CLI, and FastAPI.
+
+The full project README and architecture diagram are on
+<https://github.com/arnsri33/embedflow>.
+
+## Install
+
+```bash
+python -m pip install embedflow
+```
+
+For FAISS and the dashboard:
+
+```bash
+python -m pip install "embedflow[faiss,dashboard]"
+```
+
+Qdrant and model-runtime extras are documented in the
+[installation guide](https://github.com/arnsri33/embedflow/blob/main/docs/installation.md).
+For model-backed analysis, install `embedflow[faiss,models,dashboard]`.
+
+## Why EmbedFlow?
+
+Embedding-model upgrades usually mean re-embedding the corpus and building a
+second index before the new model can serve. EmbedFlow tests whether the
+existing retriever can remain useful during that transition.
+
+Different representation spaces can still preserve useful retrieval
+neighborhoods. EmbedFlow retrieves a bounded source candidate set, scores those
+candidates with the target model, and fills a persistent target-vector cache in
+the background.
+
+## Try it
+
+The deterministic demo needs no paid service or model download. From a source
+checkout, run:
+
+```bash
+./scripts/run_demo.sh
+```
+
+Open <http://127.0.0.1:8000/>. The first search can be `COLD` or `PARTIAL`;
+repeated traffic becomes `WARM` as target vectors are materialized.
+
+## Analyze a migration
+
+```bash
+embedflow analyze \
+  --documents ./documents.jsonl \
+  --index ./legacy.index \
+  --source-model sentence-transformers/all-MiniLM-L6-v2 \
+  --target-model Qwen/Qwen3-Embedding-0.6B \
+  --probe-queries ./probe_queries.jsonl \
+  --device cuda \
+  --output-dir ./analysis
+```
+
+The report includes the frozen T2-v1 diagnostic (`SAFE`, `EXPAND`, or
+`UNSAFE_OR_UNCERTAIN`), a recommended initial candidate depth, and ANN health.
+`SAFE` is an empirical deployment signal; validate important migrations on the
+target corpus.
+
+Start progressive serving with:
+
+```bash
+embedflow serve --config ./analysis/embedflow.analysis.yaml --device cuda
+```
+
+## Known migration evidence
+
+EmbedFlow ships a versioned registry of measured results from the research
+study. Matching model contracts provide useful starting depths and show what
+was observed on earlier corpora; a new corpus still receives its own analysis.
+
+```bash
+embedflow registry list
+embedflow registry show \
+  --source Qwen/Qwen3-Embedding-4B \
+  --target Qwen/Qwen3-Embedding-8B
+```
+
+Selected core records (nDCG@10, `G(50)`):
+
+| Source | Target | Evaluation | `G(50)` | Observed depth |
+| --- | --- | --- | ---: | ---: |
+| MiniLM-L6-v2 | Qwen3-8B | BRIGHT, 413K | 0.03665 | — |
+| Qwen3-0.6B | Qwen3-8B | BRIGHT, 413K | 0.01465 | 200 |
+| Qwen3-4B | Qwen3-8B | BRIGHT, 413K | 0.00347 | 20 |
+| MiniLM-L6-v2 | Qwen3-8B | Natural Questions, 1M | 0.03255 | 500 |
+| Qwen3-4B | Qwen3-8B | Natural Questions, 1M | -0.00043 | 20 |
+
+See the [registry documentation](https://github.com/arnsri33/embedflow/blob/main/docs/registry.md)
+for matching levels, contract fingerprints, and provenance.
+
+## Research
+
+For candidate depth `K`, EmbedFlow measures:
+
+```text
+G(K) = M_T - M_{T|S_K}
+```
+
+Lower `G(K)` means the source candidate pool recovers more of native target
+retrieval quality. Containment reports neighborhood overlap separately. The
+study includes 63 development settings, frozen BRIGHT validation, and Natural
+Questions scale experiments through 1M documents.
+
+Read the [concepts](https://github.com/arnsri33/embedflow/blob/main/docs/concepts.md)
+and [methodology](https://github.com/arnsri33/embedflow/blob/main/docs/methodology.md)
+for definitions and reproduction details.
+
+## Integrations
+
+| Backend | Status |
+| --- | --- |
+| FAISS | Supported |
+| Qdrant | Supported |
+
+See the [FAISS guide](https://github.com/arnsri33/embedflow/blob/main/docs/integrations/faiss.md)
+and [Qdrant guide](https://github.com/arnsri33/embedflow/blob/main/docs/integrations/qdrant.md).
+
+## CLI
+
+```bash
+embedflow --help
+embedflow analyze --help
+embedflow serve --config ./embedflow.yaml
+embedflow status --config ./embedflow.yaml
+embedflow registry list
+embedflow economics --corpus-size 1000000000 --docs-per-second 106.98 --gpu-price 3.29
+embedflow doctor --config ./embedflow.yaml
+```
+
+The [CLI reference](https://github.com/arnsri33/embedflow/blob/main/docs/cli.md)
+and [API reference](https://github.com/arnsri33/embedflow/blob/main/docs/api.md)
+cover the remaining commands and endpoints.
+
+## Status
+
+EmbedFlow v0.1.0 is an alpha release for research and early real-world
+testing. T2-v1 is an empirical finite-tail diagnostic, partial rankings can
+differ from fully warm target reranking, and ANN fidelity needs a reference
+comparison to audit.
+
+## Links
+
+- [GitHub repository](https://github.com/arnsri33/embedflow)
+- [Documentation](https://github.com/arnsri33/embedflow#readme)
+- [License](https://github.com/arnsri33/embedflow/blob/main/LICENSE)