5 مستودعات
Mechanisms for directing user inputs to different processing pipelines based on the nature of the request.
Distinct from Query Routing: Directs requests between retrieval and direct model response, unlike database shard routing
Explore 5 awesome GitHub repositories matching data & databases · AI Query Routing. Refine with filters or upvote what's useful.
localGPT is a private AI knowledge base and retrieval-augmented generation application. It provides a local document indexer, a hybrid search engine, and an inference interface to enable chatting with private documents and managing a self-hosted information repository without sending data to external servers. The system distinguishes itself through a dual-pass verification pipeline that ensures generated answers are grounded in retrieved sources, accompanied by explicit source attribution. It employs a hybrid retrieval approach combining semantic vector search with keyword matching and rerank
Directs requests to either retrieved document context or a direct model response based on input complexity.
Redis is a high-performance in-memory key-value store that functions as a distributed cache, message broker, and NoSQL database. It provides sub-millisecond read and write access to data stored in RAM and can operate as a vector database for indexing high-dimensional embeddings. The system supports a wide range of data storage and synchronization primitives, including the management of strings, hashes, lists, sets, and JSON documents. It enables real-time data operations through atomic transactions, hybrid persistence using snapshots and append-only logs, and high-availability configurations
Uses language models to route queries between general knowledge retrieval and specific user memories.
Manifest is a language model provider unification system that standardizes access to multiple AI backends through a single interface. It functions as a centralized management layer for integrating various cloud-based and local model providers to simplify how applications request completions. The system provides intelligent model routing and high availability infrastructure by directing queries based on complexity and automatically triggering model fallbacks when a primary provider fails. It distinguishes itself through multi-tenant AI management, organizing agents into isolated groups with de
Routes user inputs to different processing pipelines or models based on the nature of the request.
Promptbase هو إطار عمل لهندسة الأوامر مصمم لتصميم واختبار وتحسين الأوامر لنماذج اللغات الكبيرة. يوفر نظاماً لقياس دقة النموذج وأدائه من خلال مجموعة أدوات تقييم تقارن المخرجات مقابل مجموعات بيانات الحقيقة الأرضية. يتضمن المشروع أيضاً خط أنابيب تنسيق لأتمتة مهام تعلم الآلة متعددة المكونات عبر نقاط النهاية القائمة على السحابة وأداة مساعدة لإعداد مجموعات بيانات التوليد المعزز بالاسترجاع. يتميز إطار العمل بتحسين جودة الاستجابة المتقدم، باستخدام مولدات سلسلة الأفكار لإنتاج خطوات تفكير وسيطة واسترجاع أمثلة قليلة اللقطات ديناميكياً باستخدام البحث الدلالي القائم على التضمين. ينفذ طرق التجميع لزيادة الدقة التنبؤية، باستخدام توجيه الاستعلام القائم على التعقيد وتجميع تصويت الأغلبية لمتغيرات نماذج متعددة. يغطي النظام قدرات أوسع في إدارة البيانات والأتمتة، بما في ذلك تنسيق البيانات الخارجية في ملفات مهيكلة للتدريب وتنسيق خطوط أنابيب تنفيذ النموذج عبر أدوات سطر الأوامر.
Aggregates results from multiple prompt variations and routes queries based on complexity to increase predictive accuracy.
how2 is a terminal-based tool that translates plain-English questions into shell commands using AI and StackOverflow data. It functions as a command-line interface where users describe what they want to do in natural language, and the tool returns the appropriate Unix shell or PowerShell command, with support for generating multi-line Bash scripts from natural language prompts. The tool distinguishes itself through its interactive answer browsing mode, which lets users select and copy from multiple StackOverflow answers directly in the terminal. It includes a fallback search mechanism that qu
Routes queries to different AI models or search backends based on query type and user authentication status.