dynavec 0.2.0__tar.gz

dynavec-0.2.0/.env.example

@@ -0,0 +1,19 @@
+# Copy to .env and fill in. .env is gitignored — never commit real secrets.
+# dynavec reads AWS creds via the standard boto3 chain, so exporting these
+# (or loading them with python-dotenv) is enough — no code changes needed.
+
+# ---- AWS credentials (the IAM user/role that owns your dynavec resources) ----
+AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE
+AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
+AWS_REGION=us-east-1
+# AWS_SESSION_TOKEN=            # only if you use temporary/STS credentials
+
+# ---- Embedder API key (pick the provider you use) ----
+OPENAI_API_KEY=sk-...
+# GOOGLE_API_KEY=
+# COHERE_API_KEY=
+
+# ---- dynavec resource names (used by the example scripts) ----
+DYNAVEC_VECTOR_BUCKET=dynavec-demo
+DYNAVEC_INDEX=docs
+DYNAVEC_TABLE=dynavec_docs

dynavec-0.2.0/.github/workflows/ci.yml

@@ -0,0 +1,26 @@
+name: CI
+
+on:
+  push:
+    branches: [development, main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install (with dev extras)
+        run: uv pip install -e ".[dev]"
+      - name: Lint
+        run: uv run --no-sync ruff check src benchmarks
+      - name: Test
+        run: uv run --no-sync pytest -q

dynavec-0.2.0/.github/workflows/pages.yml

@@ -0,0 +1,38 @@
+name: Deploy landing page to GitHub Pages
+
+# Publishes opensource/dynavec/ to GitHub Pages.
+# One-time: repo Settings -> Pages -> Build and deployment -> Source: "GitHub Actions".
+
+on:
+  push:
+    branches: [development]
+    paths:
+      - "opensource/dynavec/**"
+      - ".github/workflows/pages.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: true
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/configure-pages@v5
+        with:
+          enablement: true
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: opensource/dynavec
+      - id: deployment
+        uses: actions/deploy-pages@v4

dynavec-0.2.0/.github/workflows/publish.yml

@@ -0,0 +1,37 @@
+name: Publish to PyPI
+
+# Publishes on a GitHub Release. Uses PyPI Trusted Publishing (OIDC) — no token
+# is stored. One-time: create a pending publisher on PyPI for project "dynavec",
+# repo "codeforstartups/dynavec", workflow "publish.yml", environment "pypi".
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Build sdist + wheel
+        run: uv build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write        # required for OIDC trusted publishing
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

dynavec-0.2.0/.gitignore

@@ -0,0 +1,25 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+.venv/
+venv/
+env/
+
+# Test / coverage
+.pytest_cache/
+.coverage
+htmlcov/
+.ruff_cache/
+
+# Editors / OS
+.vscode/
+.idea/
+.DS_Store
+
+# Local config / secrets
+.env
+*.local

dynavec-0.2.0/ARCHITECTURE.md

@@ -0,0 +1,71 @@
+# dynavec architecture
+
+## The core idea: two stores, one client
+
+A vector search returns **ids fast**; hydrating the **actual documents** is what usually costs latency and money. dynavec splits those two jobs across the AWS primitive best suited to each:
+
+| Concern | Store | Why |
+|---------|-------|-----|
+| Approximate nearest-neighbor over the embedding | **Amazon S3 Vectors** | AWS-managed ANN, serverless, scales to billions, 90%+ recall, storage priced like S3 (cheap). |
+| Full document text + rich metadata, fetched by id | **Amazon DynamoDB** | Single-digit-ms `BatchGetItem`, no per-item size cap, on-demand billing, partition-key scaling. |
+
+The vector's **key** is shared between the two stores (`"{namespace}#{id}"`), which is the join. S3 Vectors answers "which ids are nearest"; DynamoDB answers "give me those documents, now."
+
+```
+query text ──embed──▶ query_vectors (S3 Vectors) ──▶ [ (id, distance) × fetch_k ]
+                                                           │
+                                                           ▼
+                                        BatchGetItem (DynamoDB)  ──▶ full docs
+                                                           │
+                                                           ▼
+                                   MMR rerank / RRF fusion ──▶ SearchResults
+```
+
+## Why not put everything in one store?
+
+- **All in S3 Vectors:** metadata has a per-vector filterable-size cap and it's not built to be your document-of-record; reading large text back through the vector API is wasteful.
+- **All in DynamoDB:** DynamoDB has no native ANN; you'd brute-force or bolt on a secondary index and lose the serverless-ANN economics.
+- **Hybrid:** each store does the one thing it's best at. That's the whole pitch.
+
+## The metadata split
+
+On upsert, `split_metadata()` produces two payloads:
+
+- **S3 Vectors** gets a **small filterable subset** (`DynavecConfig.filterable_keys`, or all scalar keys by default) plus a namespace tag `_dv_ns`. These are the keys you can pre-filter on during ANN (`filter={"topic": "biology"}`), using the S3 Vectors MongoDB-style operators (`$eq`, `$gte`, `$in`, `$and`, `$or`, …).
+- **DynamoDB** gets the **full, untouched metadata** + the source text. Numbers are stored natively (float→Decimal) so future Global Secondary Indexes can support DynamoDB-side access patterns.
+
+Keep the filterable set small — it's the one thing with a hard size limit.
+
+## Namespaces & partitioning
+
+Every operation takes a `namespace`. It:
+- tags each vector (`_dv_ns`) so **one index can host many tenants/collections** with query-time isolation, and
+- prefixes the DynamoDB partition key (`"{namespace}#{id}"`) so load spreads evenly across partitions and hydration stays O(1) per document.
+
+This is the "DynamoDB access-pattern + partitioning logic connected to the vector store" the design calls for.
+
+## Retrieval algorithms dynavec owns
+
+S3 Vectors owns the ANN. dynavec owns everything around it:
+
+- **Score normalization** — raw distance → "higher = more similar" regardless of metric.
+- **MMR reranking** (`rerank="mmr"`) — relevance + diversity. dynavec over-fetches `top_k × over_fetch` candidates, pulls their vectors via `get_vectors`, and re-ranks.
+- **RRF hybrid fusion** (`reciprocal_rank_fusion`) — combine dense results with a sparse/keyword ranking (or several indexes) without score-scale alignment. This is the seam for hybrid search.
+
+## Multi-dimension / multi-index routing
+
+Different embedding models produce different dimensions. Because a `Dynavec` client is bound to one `(bucket, index, dimension)`, you run **one client per dimension/model** and route at the application layer (or fuse their results with RRF). Multiple S3 vector buckets → multiple dimensions, connected through the shared DynamoDB access patterns.
+
+## Roadmap: the hot tier (v0.2)
+
+This is where user-controlled ANN algorithms actually live. An optional in-process **`hnswlib`** index caches frequently-accessed partitions in memory for **sub-10-ms** queries, backed by DynamoDB for durability and S3 Vectors for the cold/scale tier. Reads check hot → warm → cold; writes fan out. SPFresh-style incremental rebalancing is the research direction for keeping the hot index fresh without full rebuilds.
+
+Also planned: async client (`aioboto3`), sparse/BM25 hybrid computed from DynamoDB, cross-encoder reranking, and LlamaIndex / CrewAI / Strands adapters.
+
+## Security & compliance
+
+- **Data residency:** DynamoDB and S3 Vectors are regional. dynavec never sends your vectors or documents anywhere except those two services in *your* account and region. Embedding is the only step that may leave the account — and only if you choose a hosted embedder (OpenAI/Gemini/Cohere). Choose `BedrockEmbedder` or `SentenceTransformerEmbedder` to keep embedding in-account/offline.
+- **IAM (least privilege):** the client needs, scoped to your specific resources:
+  - `s3vectors:PutVectors`, `s3vectors:QueryVectors`, `s3vectors:GetVectors`, `s3vectors:DeleteVectors` (+ `CreateVectorBucket`/`CreateIndex` only if using `auto_provision`)
+  - `dynamodb:BatchGetItem`, `dynamodb:BatchWriteItem`, `dynamodb:PutItem`, `dynamodb:DeleteItem` (+ `CreateTable`/`DescribeTable` for provisioning)
+- **Encryption:** both services support encryption at rest with your KMS keys; enable SSE-KMS on the table and bucket.

dynavec-0.2.0/LICENSE

@@ -0,0 +1,190 @@
+                                 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
+
+   Copyright 2026 dynavec contributors
+
+   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.