engram-search 0.1.0__tar.gz

engram_search-0.1.0/.dockerignore

@@ -0,0 +1,14 @@
+.venv/
+.git/
+.github/
+__pycache__/
+*.pyc
+.pytest_cache/
+.ruff_cache/
+benchmarks/
+tests/
+engram_store/
+*.faiss
+*.egg-info/
+dist/
+build/

engram_search-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,55 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest ruff numpy faiss-cpu
+
+      - name: Install engram
+        run: pip install -e . --no-deps
+
+      - name: Lint with ruff
+        run: ruff check engram/ tests/
+
+      - name: Run tests
+        run: pytest tests/ -v -k "not test_persistence"
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install ruff
+        run: pip install ruff
+
+      - name: Lint check
+        run: ruff check engram/ tests/
+
+      - name: Format check
+        run: ruff format --check engram/ tests/

engram_search-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,29 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

engram_search-0.1.0/.gitignore

@@ -0,0 +1,214 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Engram
+engram_store/
+*.faiss
+engram_meta.db
+benchmarks/results_*.json
+/tmp/longmemeval_*.json

engram_search-0.1.0/Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system deps
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy project files
+COPY pyproject.toml README.md LICENSE ./
+COPY engram/ engram/
+
+# Install engram with cloud + server deps
+RUN pip install --no-cache-dir -e ".[cloud]" fastapi uvicorn
+
+# Pre-download the default embedding model
+RUN python -c "from engram.retrieval.embedder import Embedder; Embedder('bge-large')._load()"
+
+EXPOSE 8000
+
+ENV ENGRAM_BACKEND=faiss
+ENV ENGRAM_STORE_PATH=/data/engram_store
+
+VOLUME ["/data"]
+
+CMD ["uvicorn", "engram.server:app", "--host", "0.0.0.0", "--port", "8000"]

engram_search-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Nitin Gupta
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

engram_search-0.1.0/PKG-INFO

@@ -0,0 +1,166 @@
+Metadata-Version: 2.4
+Name: engram-search
+Version: 0.1.0
+Summary: High-recall conversational memory retrieval. Local-first, cloud-ready. 98%+ R@5 on LongMemEval.
+Author-email: Nitin Gupta <nmittal1109@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: bm25,conversational-ai,embeddings,faiss,memory,retrieval
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+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: >=3.9
+Requires-Dist: faiss-cpu>=1.7
+Requires-Dist: numpy>=1.24
+Requires-Dist: rank-bm25>=0.2
+Requires-Dist: sentence-transformers>=3.0
+Provides-Extra: all
+Requires-Dist: pytest>=7.0; extra == 'all'
+Requires-Dist: qdrant-client>=1.9; extra == 'all'
+Requires-Dist: ruff>=0.4; extra == 'all'
+Requires-Dist: sentence-transformers>=3.0; extra == 'all'
+Requires-Dist: tqdm>=4.60; extra == 'all'
+Provides-Extra: bench
+Requires-Dist: tqdm>=4.60; extra == 'bench'
+Provides-Extra: cloud
+Requires-Dist: qdrant-client>=1.9; extra == 'cloud'
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: qdrant-client>=1.9; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Requires-Dist: sentence-transformers>=3.0; extra == 'dev'
+Requires-Dist: tqdm>=4.60; extra == 'dev'
+Provides-Extra: rerank
+Requires-Dist: sentence-transformers>=3.0; extra == 'rerank'
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <img src="logo.svg" width="180" alt="Engram logo">
+</p>
+
+<h1 align="center">Engram</h1>
+
+<p align="center">High-recall conversational memory retrieval. Local-first, cloud-ready.</p>
+
+**Target: 98%+ R@5 on LongMemEval — no LLM required.**
+
+## What It Is
+
+Engram stores conversation history and retrieves it with state-of-the-art accuracy. It uses a three-stage retrieval pipeline — dense embeddings, sparse keyword matching, and cross-encoder reranking — to achieve higher recall than systems relying on LLM-based extraction or summarization.
+
+Nothing is summarized. Nothing is paraphrased. Your exact words are stored and returned.
+
+## Why It's Better
+
+| | Engram | MemPalace | Mem0 |
+|---|---|---|---|
+| Embedding model | bge-large (1024d) | all-MiniLM (384d) | Varies |
+| Sparse retrieval | BM25 with RRF fusion | Ad-hoc keyword overlap | N/A |
+| Reranking | Cross-encoder (free) | LLM call ($0.001/q) | N/A |
+| Indexing | User + assistant turns | User turns only | LLM-extracted facts |
+| Cloud deployment | Qdrant backend | No | Yes |
+| LLM required | No | No (optional rerank) | Yes |
+
+## Install
+
+```bash
+# Local mode (FAISS + SQLite)
+pip install engram
+
+# With cloud backend (Qdrant)
+pip install engram[cloud]
+
+# With cross-encoder reranker
+pip install engram[rerank]
+
+# Everything
+pip install engram[all]
+```
+
+## Quickstart — Local Mode
+
+```bash
+# Initialize a memory store
+engram init ./my_memories
+
+# Ingest conversations
+engram ingest conversations.json --store ./my_memories
+
+# Search
+engram search "why did we switch to GraphQL" --store ./my_memories
+```
+
+## Quickstart — Cloud Mode (for companies)
+
+```bash
+# Set up Qdrant (managed or self-hosted)
+export ENGRAM_BACKEND=qdrant
+export ENGRAM_QDRANT_URL=https://your-cluster.qdrant.io:6333
+export ENGRAM_QDRANT_API_KEY=your-api-key
+
+# Start the API server
+pip install fastapi uvicorn
+uvicorn engram.server:app --host 0.0.0.0 --port 8000
+```
+
+API endpoints:
+- `POST /ingest` — add conversations
+- `POST /search` — search memories
+- `GET /health` — health check
+- `GET /stats` — store statistics
+
+## Benchmarks
+
+```bash
+# Download LongMemEval dataset
+mkdir -p /tmp/longmemeval-data
+curl -fsSL -o /tmp/longmemeval-data/longmemeval_s_cleaned.json \
+  https://huggingface.co/datasets/xiaowu0162/longmemeval-cleaned/resolve/main/longmemeval_s_cleaned.json
+
+# Run benchmark
+pip install -e ".[dev]"
+
+# Dense only (bge-large baseline)
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode dense
+
+# Hybrid (dense + BM25 via RRF) — default
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode hybrid
+
+# Full pipeline (hybrid + cross-encoder reranker)
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode rerank
+```
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                        Engram                               │
+│                                                             │
+│  ┌────────────┐  ┌─────────────┐  ┌───────────────────┐    │
+│  │ Ingestion  │  │   Index     │  │    Retrieval      │    │
+│  │            │→ │             │→ │                   │    │
+│  │ user+asst  │  │ FAISS (local│  │ 1. Dense (bi-enc) │    │
+│  │ turns      │  │  or Qdrant  │  │ 2. BM25 (sparse)  │    │
+│  │ preference │  │ (cloud)     │  │ 3. RRF fusion     │    │
+│  │ extraction │  │             │  │ 4. Cross-encoder   │    │
+│  └────────────┘  └─────────────┘  └───────────────────┘    │
+│                                                             │
+│  Local: FAISS + SQLite    Cloud: Qdrant + REST API          │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Requirements
+
+- Python 3.10+
+- ~1.3 GB disk for bge-large embedding model (downloaded on first use)
+- No API key required for local mode
+
+## License
+
+MIT

engram_search-0.1.0/README.md

@@ -0,0 +1,124 @@
+<p align="center">
+  <img src="logo.svg" width="180" alt="Engram logo">
+</p>
+
+<h1 align="center">Engram</h1>
+
+<p align="center">High-recall conversational memory retrieval. Local-first, cloud-ready.</p>
+
+**Target: 98%+ R@5 on LongMemEval — no LLM required.**
+
+## What It Is
+
+Engram stores conversation history and retrieves it with state-of-the-art accuracy. It uses a three-stage retrieval pipeline — dense embeddings, sparse keyword matching, and cross-encoder reranking — to achieve higher recall than systems relying on LLM-based extraction or summarization.
+
+Nothing is summarized. Nothing is paraphrased. Your exact words are stored and returned.
+
+## Why It's Better
+
+| | Engram | MemPalace | Mem0 |
+|---|---|---|---|
+| Embedding model | bge-large (1024d) | all-MiniLM (384d) | Varies |
+| Sparse retrieval | BM25 with RRF fusion | Ad-hoc keyword overlap | N/A |
+| Reranking | Cross-encoder (free) | LLM call ($0.001/q) | N/A |
+| Indexing | User + assistant turns | User turns only | LLM-extracted facts |
+| Cloud deployment | Qdrant backend | No | Yes |
+| LLM required | No | No (optional rerank) | Yes |
+
+## Install
+
+```bash
+# Local mode (FAISS + SQLite)
+pip install engram
+
+# With cloud backend (Qdrant)
+pip install engram[cloud]
+
+# With cross-encoder reranker
+pip install engram[rerank]
+
+# Everything
+pip install engram[all]
+```
+
+## Quickstart — Local Mode
+
+```bash
+# Initialize a memory store
+engram init ./my_memories
+
+# Ingest conversations
+engram ingest conversations.json --store ./my_memories
+
+# Search
+engram search "why did we switch to GraphQL" --store ./my_memories
+```
+
+## Quickstart — Cloud Mode (for companies)
+
+```bash
+# Set up Qdrant (managed or self-hosted)
+export ENGRAM_BACKEND=qdrant
+export ENGRAM_QDRANT_URL=https://your-cluster.qdrant.io:6333
+export ENGRAM_QDRANT_API_KEY=your-api-key
+
+# Start the API server
+pip install fastapi uvicorn
+uvicorn engram.server:app --host 0.0.0.0 --port 8000
+```
+
+API endpoints:
+- `POST /ingest` — add conversations
+- `POST /search` — search memories
+- `GET /health` — health check
+- `GET /stats` — store statistics
+
+## Benchmarks
+
+```bash
+# Download LongMemEval dataset
+mkdir -p /tmp/longmemeval-data
+curl -fsSL -o /tmp/longmemeval-data/longmemeval_s_cleaned.json \
+  https://huggingface.co/datasets/xiaowu0162/longmemeval-cleaned/resolve/main/longmemeval_s_cleaned.json
+
+# Run benchmark
+pip install -e ".[dev]"
+
+# Dense only (bge-large baseline)
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode dense
+
+# Hybrid (dense + BM25 via RRF) — default
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode hybrid
+
+# Full pipeline (hybrid + cross-encoder reranker)
+python benchmarks/longmemeval_bench.py /tmp/longmemeval-data/longmemeval_s_cleaned.json --mode rerank
+```
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                        Engram                               │
+│                                                             │
+│  ┌────────────┐  ┌─────────────┐  ┌───────────────────┐    │
+│  │ Ingestion  │  │   Index     │  │    Retrieval      │    │
+│  │            │→ │             │→ │                   │    │
+│  │ user+asst  │  │ FAISS (local│  │ 1. Dense (bi-enc) │    │
+│  │ turns      │  │  or Qdrant  │  │ 2. BM25 (sparse)  │    │
+│  │ preference │  │ (cloud)     │  │ 3. RRF fusion     │    │
+│  │ extraction │  │             │  │ 4. Cross-encoder   │    │
+│  └────────────┘  └─────────────┘  └───────────────────┘    │
+│                                                             │
+│  Local: FAISS + SQLite    Cloud: Qdrant + REST API          │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Requirements
+
+- Python 3.10+
+- ~1.3 GB disk for bge-large embedding model (downloaded on first use)
+- No API key required for local mode
+
+## License
+
+MIT