{"id":45586677,"url":"https://github.com/afriddev/cortexvia","last_synced_at":"2026-02-23T11:54:37.028Z","repository":{"id":317521299,"uuid":"1067316961","full_name":"afriddev/cortexvia","owner":"afriddev","description":"Cortexvia – Empowering AI-driven knowledge retrieval and inference. ","archived":false,"fork":false,"pushed_at":"2025-12-17T20:48:11.000Z","size":29323,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-21T08:46:19.938Z","etag":null,"topics":["chatbot","fastapi","llm","rag"],"latest_commit_sha":null,"homepage":"https://cortexvia.vercel.app","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/afriddev.png","metadata":{"files":{"readme":"README.md","changelog":null,"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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-30T17:24:10.000Z","updated_at":"2025-12-17T20:48:15.000Z","dependencies_parsed_at":"2025-10-01T13:21:28.943Z","dependency_job_id":"24b6f0c6-42f1-4ae3-8261-ada901b23ea5","html_url":"https://github.com/afriddev/cortexvia","commit_stats":null,"previous_names":["afriddev/aifolio-ui","afriddev/cortexvia"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/afriddev/cortexvia","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afriddev%2Fcortexvia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afriddev%2Fcortexvia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afriddev%2Fcortexvia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afriddev%2Fcortexvia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/afriddev","download_url":"https://codeload.github.com/afriddev/cortexvia/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afriddev%2Fcortexvia/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29741942,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T07:44:07.782Z","status":"ssl_error","status_checked_at":"2026-02-23T07:44:07.432Z","response_time":90,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["chatbot","fastapi","llm","rag"],"created_at":"2026-02-23T11:54:36.259Z","updated_at":"2026-02-23T11:54:37.005Z","avatar_url":"https://github.com/afriddev.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **Cortexvia Documentation**\n\nCortexvia is a powerful AI platform built to fulfill diverse needs — whether you’re a **developer**, **enterprise**, or **business owner**. Cortexvia offers cutting-edge tools, APIs, and SDKs that make it easy to integrate AI and automation into your applications and workflows.\n\n---\n\n## **Who Cortexvia Is For**\n\n- **For Developers —** Build intelligent, AI-powered applications using Cortexvia’s unified API and SDK ecosystem. Access multiple models with one key.\n- **For Businesses —** Leverage AI to automate operations, enhance customer experiences, and unlock data-driven growth.\n\n---\n\n##  **About Cortexvia**\n\nCortexvia is a next-generation AI infrastructure platform designed to make advanced large language models (LLMs), RAG pipelines, and automation tools accessible to everyone.  \nOur mission is simple — **empower developers and organizations to create, innovate, and scale** using AI.\n\n---\n\n##  **What Cortexvia Offers**\n\n### **AI Models**\nAccess multiple high-performance `LLMs` for natural language understanding, generation, and reasoning. Choose the right model based on size, speed, and capability.\n\n### **API Inference**\nIntegrate Cortexvia’s AI models into your products using developer-friendly REST APIs.  \n- Compatible with **OpenAI SDKs** and standard completion endpoints.  \n- Fast integration, flexible usage, and scalable deployment.\n\n### **Developer SDKs**\nCortexvia provides open-source SDKs and libraries for rapid development:\n- **CortexRAG** – Build Retrieval-Augmented Generation (RAG) systems with multiple strategies:\n  - **RAG:** Basic chunk-based vector retrieval.\n  - **Smart RAG:** Uses LLM-generated questions + embeddings for deeper retrieval.\n  - **Light RAG:** Optimized for speed and efficiency.\n  - **Graph RAG:** Builds a knowledge graph for relational and context-aware retrieval.\n- **EmbiRankis** – Generate high-quality embeddings and rerank results for improved accuracy.\n- **Chatbot Library** – A React-based AI Chatbot SDK for building intelligent chat experiences.\n- **Business Chatbot** – Specialized toolkit for enterprise-grade customer chat automation.\n\n---\n\n##  **Getting Started**\n\n1. Visit [**Cortexvia.com**](https://cortexvia.com)  \n2. Create your free account.  \n3. Explore documentation, APIs, and SDKs.  \n4. Start building your AI-powered applications instantly.\n\n---\n\n## **Business Chatbot Query \u0026 Speed Limits**\n\n### **Document \u0026 Video Limits**\n| Limit Type | Free Tier | Developer Tier | Enterprise |\n|-------------|------------|----------------|-------------|\n| **Document Uploads** | 2 files/day (max 50MB each) | 200 files/day (max 100MB each) | Custom / Unlimited |\n| **Supported Formats** | PDF | PDF, DOCX, TXT, Markdown | All text-based formats |\n| **Video Uploads** | 1 YouTube URL/day | 50 URLs/day | Unlimited |\n| **Processing Speed** | Standard Queue (up to 2 mins) | Priority Queue (10–30 sec) | Instant / Batch Upload API |\n\n### **Query \u0026 Message Limits**\n| Parameter | Free Tier | Developer Tier | Enterprise |\n|------------|------------|----------------|-------------|\n| **Daily Queries** | 100 / day | Unlimited / day | Unlimited |\n| **Messages per Conversation** | 10 messages | \u003c 100 messages | Unlimited |\n| **Context Memory** | 4K Tokens | 64K Tokens | 128K+ Tokens |\n\n### **⚡ Query Speed Tiers**\n| Speed Tier | Rate | Description |\n|-------------|------|-------------|\n| **Low Speed** | 50–200 Tokens/sec | Balanced mode for detailed, reasoning-heavy answers. Default for Free Tier. |\n| **Medium Speed** | 100–2000 Tokens/sec | Optimized for faster document retrieval and chat responses. Default for Developer Tier. |\n| **High Speed (Flash)** | 1000–3000 Tokens/sec | For production-grade RAG and real-time applications. Flash \u0026 Ultra models only. |\n\n\u003e ⏱️ All **data and query limits refresh every 24 hours**.  \n\u003e Upgrade your tier for **faster indexing**, **larger uploads**, and **higher query throughput**.\n\n---\n\n##  **AI Models Overview**\n\nCortexvia offers optimized LLM models under **Free** and **Developer** tiers.  \nChoose based on speed, capability, and usage volume.\n\n### **Free Tier Models**\n| Model | Size | Speed | RPM | RPD | TPM | TPD |\n|-------|------|--------|------|------|------|------|\n| Cortexvia Mini | 8B | 150 TPS | 20 req/min | 800 req/day | 100K Tokens/min | 400K Tokens/day |\n| Cortexvia Nemo | 12B | 180 TPS | 40 req/min | 2000 req/day | 50K Tokens/min | 200K Tokens/day |\n| Cortexvia Small | 24B | 120 TPS | 20 req/min | 500 req/day | 150K Tokens/min | 1000K Tokens/day |\n| Cortexvia Medium | 49B | 100 TPS | 40 req/min | 500 req/day | 100K Tokens/min | 300K Tokens/day |\n| Cortexvia Large | 123B | 50 TPS | 20 req/min | 1500 req/day | 100K Tokens/min | 300K Tokens/day |\n| Cortexvia Flash Mini | 8B | 2200 TPS | 10 req/min | 5000 req/day | 30K Tokens/min | 100K Tokens/day |\n| Cortexvia Flash Small | 70B | 2100 TPS | 20 req/min | 5000 req/day | 30K Tokens/min | 100K Tokens/day |\n| Cortexvia Flash Medium | 109B | 2600 TPS | 15 req/min | 5000 req/day | 30K Tokens/min | 100K Tokens/day |\n\n---\n\n### **Developer Tier Models**\n| Model | Size | Speed | RPM | RPD | TPM | TPD |\n|-------|------|--------|------|------|------|------|\n| Cortexvia Mini | 8B | 150 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 6M Tokens/day |\n| Cortexvia Nemo | 12B | 180 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 5M Tokens/day |\n| Cortexvia Small | 24B | 120 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 4M Tokens/day |\n| Cortexvia Medium | 49B | 100 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 4M Tokens/day |\n| Cortexvia Large | 123B | 50 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 1M Tokens/day |\n| Cortexvia Ultra | 235B | 60 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 2M Tokens/day |\n| Cortexvia Flash Mini | 8B | 2200 TPS | 60 req/min | 20K req/day | 100K Tokens/min | 1M Tokens/day |\n| Cortexvia Flash Small | 70B | 2100 TPS | 60 req/min | 14K req/day | 60K Tokens/min | 1M Tokens/day |\n| Cortexvia Flash Medium | 109B | 2600 TPS | 60 req/min | 14K req/day | 60K Tokens/min | 1M Tokens/day |\n| Cortexvia Flash Super | 235B | 1500 TPS | 60 req/min | 14K req/day | 60K Tokens/min | 1M Tokens/day |\n| Cortexvia Ultra Flash | 120B | 3000 TPS | 60 req/min | 14K req/day | 60K Tokens/min | 1M Tokens/day |\n\n---\n\n## **Cortexvia Metric Definitions**\n| Metric | Full Form | Example |\n|---------|------------|----------|\n| **TPS** | Tokens Per Second | `150 TPS` = ~150 tokens/sec |\n| **RPM** | Requests Per Minute | `60 req/min` = 60 requests every 60 seconds |\n| **RPD** | Requests Per Day | `20K req/day` = 20,000 daily requests |\n| **TPM** | Tokens Per Minute | `100K Tokens/min` = 100,000 Tokens/minute |\n| **TPD** | Tokens Per Day | `6M Tokens/day` = 6 million Tokens/day |\n\n---\n\n###  **Additional Notes**\n- **Request:** A single API call or message completion counts as one request.  \n- **Speed Tier:** Defined by _TPS_ — higher values mean faster model performance.  \n- **Limits Reset:** RPM and RPD automatically reset every minute and every 24 hours.  \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fafriddev%2Fcortexvia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fafriddev%2Fcortexvia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fafriddev%2Fcortexvia/lists"}