{"id":28677479,"url":"https://github.com/analyticsinmotion/symrank","last_synced_at":"2025-06-14T00:06:27.416Z","repository":{"id":294823060,"uuid":"988128543","full_name":"analyticsinmotion/symrank","owner":"analyticsinmotion","description":"🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.","archived":false,"fork":false,"pushed_at":"2025-05-29T13:22:25.000Z","size":676,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-05-29T14:12:59.292Z","etag":null,"topics":["cosine-similarity","python-rust","rag","ranking-system","reranking","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/analyticsinmotion.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-22T05:15:32.000Z","updated_at":"2025-05-29T13:00:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"a3af3a3d-ffbd-4270-9d3d-6f3611de846e","html_url":"https://github.com/analyticsinmotion/symrank","commit_stats":null,"previous_names":["analyticsinmotion/symrank"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/analyticsinmotion/symrank","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/analyticsinmotion%2Fsymrank","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/analyticsinmotion%2Fsymrank/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/analyticsinmotion%2Fsymrank/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/analyticsinmotion%2Fsymrank/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/analyticsinmotion","download_url":"https://codeload.github.com/analyticsinmotion/symrank/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/analyticsinmotion%2Fsymrank/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259737929,"owners_count":22903874,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cosine-similarity","python-rust","rag","ranking-system","reranking","retrieval-augmented-generation"],"created_at":"2025-06-14T00:06:26.694Z","updated_at":"2025-06-14T00:06:27.395Z","avatar_url":"https://github.com/analyticsinmotion.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![logo-symrank](https://github.com/user-attachments/assets/ce0b2224-d59a-4aab-a708-dcdc4968c54a)\n\n\u003ch1 align=\"center\"\u003eSimilarity ranking for Retrieval-Augmented Generation\u003c/h1\u003e\n\n\u003c!-- badges: start --\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ctable\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cstrong\u003eMeta\u003c/strong\u003e\u003c/td\u003e\n      \u003ctd\u003e\n        \u003ca href=\"https://pypi.org/project/symrank/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/symrank?label=PyPI\u0026color=blue\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://www.python.org/downloads/\"\u003e\u003cimg src=\"https://img.shields.io/badge/python-3.10%7C3.11%7C3.12%7C3.13-blue?logo=python\u0026logoColor=ffdd54\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://github.com/analyticsinmotion/symrank/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-Apache_2.0-blue.svg\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://github.com/astral-sh/uv\"\u003e\u003cimg src=\"https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json\" alt=\"uv\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://github.com/astral-sh/ruff\"\u003e\u003cimg src=\"https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json\" alt=\"Ruff\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://www.rust-lang.org\"\u003e\u003cimg src=\"https://img.shields.io/badge/Powered%20by-Rust-black?logo=rust\u0026logoColor=white\" alt=\"Powered by Rust\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://github.com/analyticsinmotion\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/analyticsinmotion/.github/main/assets/images/analytics-in-motion-github-badge-rounded.svg\" alt=\"Analytics in Motion\"\u003e\u003c/a\u003e\n        \u003c!-- \u0026nbsp;\n        \u003ca href=\"https://pypi.org/project/symrank/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/dm/symrank?label=PyPI%20downloads\"\u003e\u003c/a\u003e\u0026nbsp;\n        \u003ca href=\"https://pepy.tech/project/symrank\"\u003e\u003cimg src=\"https://static.pepy.tech/badge/symrank\"\u003e\u003c/a\u003e\n        --\u003e\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/table\u003e\n\u003c/div\u003e\n\n\u003c!-- badges: end --\u003e\n\n## ✨ What is SymRank?\n**SymRank** is a blazing-fast Python library for top-k cosine similarity ranking, designed for vector search, retrieval-augmented generation (RAG), and embedding-based matching.\n\nBuilt with a Rust + SIMD backend, it offers the speed of native code with the ease of Python.\n\n\u003cbr/\u003e\n\n## 🚀 Why SymRank?\n\n⚡ Fast: SIMD-accelerated cosine scoring with adaptive parallelism\n\n🧠 Smart: Automatically selects serial or parallel mode based on workload\n\n🔢 Top-K optimized: Efficient inlined heap selection (no full sort overhead)\n\n🐍 Pythonic: Easy-to-use Python API\n\n🦀 Powered by Rust: Safe, high-performance core engine\n\n📉 Memory Efficient: Supports batching for speed and to reduce memory footprint\n\n\u003cbr/\u003e\n\n## 📦 Installation\n\nYou can install SymRank with 'uv' or alternatively using 'pip'.\n\n### Recommended (with uv):\n```bash\nuv pip install symrank\n```\n\n### Alternatively (using pip):\n```bash\npip install symrank\n```\n\n\u003cbr/\u003e\n\n## 🧪 Usage\n\n### Basic Example (using python lists)\n\n```python\nimport symrank as sr\n\nquery = [0.1, 0.2, 0.3, 0.4]  \ncandidates = [\n    (\"doc_1\", [0.1, 0.2, 0.3, 0.5]),\n    (\"doc_2\", [0.9, 0.1, 0.2, 0.1]),\n    (\"doc_3\", [0.0, 0.0, 0.0, 1.0]),\n]\n\nresults = sr.cosine_similarity(query, candidates, k=2)\nprint(results)\n```\n\n*Output*\n```python\n[{'id': 'doc_1', 'score': 0.9939991235733032}, {'id': 'doc_3', 'score': 0.7302967309951782}]\n```\n\n### Basic Example (using numpy arrays)\n\n```python\nimport symrank as sr\nimport numpy as np\n\nquery = np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32)\ncandidates = [\n    (\"doc_1\", np.array([0.1, 0.2, 0.3, 0.5], dtype=np.float32)),\n    (\"doc_2\", np.array([0.9, 0.1, 0.2, 0.1], dtype=np.float32)),\n    (\"doc_3\", np.array([0.0, 0.0, 0.0, 1.0], dtype=np.float32)),\n]\n\nresults = sr.cosine_similarity(query, candidates, k=2)\nprint(results)\n```\n\n*Output*\n```python\n[{'id': 'doc_1', 'score': 0.9939991235733032}, {'id': 'doc_3', 'score': 0.7302967309951782}]\n```\n\n\u003cbr/\u003e\n\n## 🧩 API: cosine_similarity(...)\n\n```python\ncosine_similarity(\n    query_vector,              # List[float] or np.ndarray\n    candidate_vectors,         # List[Tuple[str, List[float] or np.ndarray]]\n    k=5,                       # Number of top results to return\n    batch_size=None            # Optional: set for memory-efficient batching\n)\n```\n\n### 'cosine_similarity(...)' Parameters\n\n| Parameter         | Type                                               | Default     | Description |\n|-------------------|----------------------------------------------------|-------------|-------------|\n| `query_vector`     | `list[float]` or `np.ndarray`                       | _required_  | The query vector you want to compare against the candidate vectors. |\n| `candidate_vectors`| `list[tuple[str, list[float] or np.ndarray]]`          | _required_  | List of `(id, vector)` pairs. Each vector can be a list or NumPy array. |\n| `k`                | `int`                                               | 5         | Number of top results to return, sorted by descending similarity. |\n| `batch_size`       | `int` or `None`                                       | None      | Optional batch size to reduce memory usage. If None, uses SIMD directly. |\n\n### Returns\n\nList of dictionaries with `id` and `score` (cosine similarity), sorted by descending similarity:\n\n```python\n[{\"id\": \"doc_42\", \"score\": 0.8763}, {\"id\": \"doc_17\", \"score\": 0.8451}, ...]\n```\n\n\n\u003cbr/\u003e\n\n## 📄 License\n\nThis project is licensed under the Apache License 2.0.\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanalyticsinmotion%2Fsymrank","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanalyticsinmotion%2Fsymrank","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanalyticsinmotion%2Fsymrank/lists"}