build: support Python 3.11+ and verify the range in CI

.github/workflows/ci.yml

@@ -38,16 +38,25 @@ jobs:
         run: ruff check src tests setups
 
   test:
-    name: Tests
+    name: Tests (py${{ matrix.python-version }})
     runs-on: ubuntu-latest
     timeout-minutes: 20
 
+    strategy:
+      # Every supported interpreter reports independently, so one broken
+      # version never masks the others.
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
       - name: Setup Pipenv
         uses: ./.github/actions/setup-pipenv
+        with:
+          python-version: ${{ matrix.python-version }}
 
       # Auto-discovers every test file so new tests can never be silently skipped.
       - name: Run tests

Pipfile

@@ -31,4 +31,4 @@ mkdocs-mermaid2-plugin = "*"
 linkchecker = "*"
 
 [requires]
-python_version = "3.13"
+python_version = ">=3.11"

README.md

@@ -2,7 +2,7 @@
 
 A local-first research pipeline that retrieves academic papers from multiple scholarly APIs, ranks and clusters them with embeddings, synthesizes cross-paper insights, and exports reports in several formats. Uses **Ollama** by default for fully local LLM inference, with optional **OpenAI** and **Anthropic** providers.
 
-Built with Python 3.13, pydantic-ai, sentence-transformers, and async I/O.
+Built with Python 3.11+, pydantic-ai, sentence-transformers, and async I/O.
 
 **Documentation:** [https://ndevu12.github.io/Research_Assistant_Model/](https://ndevu12.github.io/Research_Assistant_Model/) — architecture, configuration, API reference, and operations.
 
@@ -17,7 +17,7 @@ Built with Python 3.13, pydantic-ai, sentence-transformers, and async I/O.
 
 ## Requirements
 
-- Python 3.13+ and [Pipenv](https://pipenv.pypa.io/)
+- Python 3.11+ and [Pipenv](https://pipenv.pypa.io/)
 - Internet access for paper retrieval (LLM inference can run fully offline after model download)
 
 | Local model | RAM | Disk |
@@ -30,9 +30,9 @@ Cloud providers require only an API key — no Ollama install.
 ## Quick start
 
 ```bash
-pip install pipenv
+pip install pipenv            # externally-managed distro (Arch, Debian 12+, Fedora 39+)? use: pipx install pipenv
 pipenv install
-cp .env.example .env          # optional; edit as needed
+cp -n .env.example .env       # optional; -n leaves an existing .env untouched
 pipenv run python -m src "transformer attention mechanisms"
 ```
 

docs/development/local-setup.md

@@ -1,14 +1,14 @@
 # Local Development Setup
 
-Development environment for AI Research Assistant: Python 3.13, Pipenv, pytest, and optional docs tooling.
+Development environment for AI Research Assistant: Python 3.11+, Pipenv, pytest, and optional docs tooling.
 
 Source: `Pipfile`, `README.md`, `src/__main__.py`.
 
 ## Prerequisites
 
 | Requirement | Notes |
 |-------------|-------|
-| Python 3.13+ | Pinned in `Pipfile` `[requires]` |
+| Python 3.11+ | Floor declared in `Pipfile` `[requires]` (`>=3.11`) |
 | Pipenv | Virtualenv and lockfile management |
 | Git | Clone the repository |
 
@@ -19,9 +19,9 @@ For LLM development with Ollama, run [Setup system — Quick start](../setup-sys
 ```bash
 git clone https://github.com/Ndevu12/Research_Assistant_Model.git
 cd Research_Assistant_Model
-pip install pipenv
+pip install pipenv     # externally-managed distro (Arch, Debian 12+, Fedora 39+)? use: pipx install pipenv
 pipenv install --dev
-cp .env.example .env   # optional
+cp -n .env.example .env   # optional; -n leaves an existing .env untouched
 ```
 
 `pipenv install --dev` installs:

docs/getting-started/installation.md

@@ -10,7 +10,7 @@ This page covers what gets installed, layout, and verification — not repeated
 
 | Requirement | Version / notes |
 |-------------|-----------------|
-| Python | 3.13+ |
+| Python | 3.11+ (tested on 3.11–3.14) |
 | Pipenv | Dependency and virtualenv management |
 | Internet | API retrieval; optional after Ollama model download for local LLM |
 | RAM (local LLM) | 4–6 GB (`llama3.2:3b`) or 8–10 GB (`llama3.1:8b`) |

docs/index.md

@@ -2,7 +2,7 @@
 
 A local-first research pipeline that retrieves academic papers from multiple scholarly APIs, ranks and clusters them with embeddings, synthesizes cross-paper insights, and exports reports in several formats. Uses **Ollama** by default for fully local LLM inference, with optional **OpenAI** and **Anthropic** providers.
 
-Built with Python 3.13, pydantic-ai, sentence-transformers, and async I/O.
+Built with Python 3.11+, pydantic-ai, sentence-transformers, and async I/O.
 
 Feature list, requirements, and RAM guidance: [README](https://github.com/Ndevu12/Research_Assistant_Model#features).
 
@@ -13,7 +13,7 @@ Feature list, requirements, and RAM guidance: [README](https://github.com/Ndevu1
 
 | Section | Description |
 |---------|-------------|
-| [Installation](getting-started/installation.md) | Pipenv, Python 3.13, dependencies |
+| [Installation](getting-started/installation.md) | Pipenv, Python 3.11+, dependencies |
 | [Quick Start](getting-started/quick-start.md) | First query and auto-setup flow |
 | [CLI Reference](user-guide/cli.md) | Flags, batch vs interactive mode |
 | [CLI vs API](user-guide/cli-vs-api.md) | Execution paths and provider divergence |

pyproject.toml

@@ -10,7 +10,7 @@ markers = [
 
 [tool.ruff]
 line-length = 100
-target-version = "py313"
+target-version = "py311"
 
 [tool.ruff.lint]
 # Correctness-focused: syntax errors, undefined names, unused imports/variables.