Business Software for Fireworks AI

Introducing the next iteration of our open-source large language model, this version features model weights along with initial code for the pretrained and fine-tuned Llama language models, which span from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been developed using an impressive 2 trillion tokens and offer double the context length compared to their predecessor, Llama 1. Furthermore, the fine-tuned models have been enhanced through the analysis of over 1 million human annotations. Llama 2 demonstrates superior performance against various other open-source language models across multiple external benchmarks, excelling in areas such as reasoning, coding capabilities, proficiency, and knowledge assessments. For its training, Llama 2 utilized publicly accessible online data sources, while the fine-tuned variant, Llama-2-chat, incorporates publicly available instruction datasets along with the aforementioned extensive human annotations. Our initiative enjoys strong support from a diverse array of global stakeholders who are enthusiastic about our open approach to AI, including companies that have provided valuable early feedback and are eager to collaborate using Llama 2. The excitement surrounding Llama 2 signifies a pivotal shift in how AI can be developed and utilized collectively.

Assembly sharpens your entire development perspective, ensuring you begin each day with a clear vision. This innovative platform is set to transform software development by merging understanding, planning, coding, reviewing, and documentation into an integrated framework. Acting as the central hub for development teams, Factory provides customized dashboards that showcase pertinent tasks and optimize workflows, guaranteeing both clarity and productivity from the outset of each day. It supports collaborative design and strategic planning, enabling teams to efficiently create architectures, articulate requirements, and devise technical roadmaps. Furthermore, the codebase Q&A functionality enhances onboarding and knowledge transfer by preserving context and decision-making processes, making it easier to grasp intricate systems. In addition, Factory's AI-enhanced code review mechanism thoroughly analyzes codebases, pinpointing nuanced problems and facilitating effective implementation of feedback for continuous improvement. This comprehensive approach not only elevates individual productivity but also fosters a culture of collaboration and innovation within development teams.

Inworld TTS stands out as a cutting-edge text-to-speech solution that provides exceptionally realistic and context-aware speech synthesis alongside advanced voice-cloning features, all at an incredibly affordable price. Its leading model, TTS-1, is tailored for real-time usage, boasting low-latency streaming capabilities—where the first audio segment is available in about 200 milliseconds—and supports a wide array of languages such as English, Spanish, French, Korean, Chinese, and several others. Developers have the flexibility to utilize instant zero-shot voice cloning, requiring only 5 to 15 seconds of audio input, or opt for more detailed fine-tuned cloning, enabling the addition of voice-tags that convey emotion, style, and non-verbal cues, while also allowing for language switching without losing the unique voice identity. For those seeking even greater expressiveness and multilingual capabilities, the TTS-1-Max model is currently in preview, offering enhanced features. The platform accommodates various access methods, including API and portal options, and can operate in either streaming or batch modes, making it suitable for a diverse range of applications such as interactive voice agents, gaming characters, and bespoke audio branding experiences. With its versatility and advanced technology, Inworld TTS is poised to revolutionize how we interact with synthetic voices.

Outspeed delivers advanced networking and inference capabilities designed to facilitate the rapid development of voice and video AI applications in real-time. This includes AI-driven speech recognition, natural language processing, and text-to-speech technologies that power intelligent voice assistants, automated transcription services, and voice-operated systems. Users can create engaging interactive digital avatars for use as virtual hosts, educational tutors, or customer support representatives. The platform supports real-time animation and fosters natural conversations, enhancing the quality of digital interactions. Additionally, it offers real-time visual AI solutions for various applications, including quality control, surveillance, contactless interactions, and medical imaging assessments. With the ability to swiftly process and analyze video streams and images with precision, it excels in producing high-quality results. Furthermore, the platform enables AI-based content generation, allowing developers to create extensive and intricate digital environments efficiently. This feature is particularly beneficial for game development, architectural visualizations, and virtual reality scenarios. Adapt's versatile SDK and infrastructure further empower users to design custom multimodal AI solutions by integrating different AI models, data sources, and interaction methods, paving the way for groundbreaking applications. The combination of these capabilities positions Outspeed as a leader in the AI technology landscape.

Scribe is an automated knowledge base that operates on a self-hosted platform, utilizing your tools to generate content. It analyzes the Git history, Claude Code and Codex sessions, as well as self-sent URLs and drop files, transforming this information into a well-organized, cross-project wiki formatted in Markdown and stored within Git repositories. By eliminating the need for developers to maintain an additional cognitive framework or to reconstruct context each time an agent session begins anew, Scribe effectively captures critical decisions, fixes, evaluations, and the rationale behind them, enabling agents to reference this accumulated knowledge prior to taking action. Its operational pipeline is scheduled via cron jobs, allowing it to identify projects and sift through low-value data using FTS5 before engaging with an LLM, thus extracting verified facts through structured bounded workflows that run in two passes. The final output is organized into entity-centric pages complete with YAML frontmatter, wikilinks, backlinks, retrieval context, and various typed relationships, including supersedes, contradicts, derived_from, specializes, and extends, ensuring comprehensive documentation and clarity across projects. This systematic approach significantly enhances collaboration and knowledge sharing among teams, streamlining the development process.

Router acts as a gateway designed to lower inference costs by selecting the most cost-effective model that satisfies performance requirements for each request. It simplifies access for developers by providing a single endpoint and API key, allowing them to utilize a variety of both closed and open-source AI models from numerous providers, including OpenAI, Anthropic, Grok, and Fireworks, thereby eliminating the need to connect to each provider individually. Initially, requests are processed through Router, which enables tracking of usage, model selection, provider information, and associated costs, ensuring that workloads are efficiently directed to alternative options when quality remains intact. With Router Strategies, developers can establish their own cost and performance priorities for different request types or rely on pre-set benchmarks derived from actual production experiences. The system is responsive to real-time conditions such as latency, availability, failures, and rate limits, allowing for the seamless rerouting of eligible requests to other available models when a particular provider is unable to fulfill them. This flexibility enhances the overall efficiency and reliability of the service, ensuring that developers can meet their application demands effectively.

FireWorks offers a comprehensive solution designed specifically for Fire Stations and EMS, featuring an integrated workflow that allows you to efficiently oversee all departmental requirements. This all-in-one software not only streamlines operations but also connects vital functions of a Fire Rescue Department, encompassing both Suppression and Prevention through its Pre-Plan and Inspection system. Fire crews can perform pre-plan surveys seamlessly alongside fire inspectors who carry out their routine inspections. Essential data, including emergency contact details, knox box locations, FACP placements, and recent inspection violations, can be accessed conveniently from any mobile device. Moreover, information updated during the Prevention phase of inspections and the Suppression pre-planning is instantly refreshed, ensuring all users have real-time access to the latest data. FireWorks stands out as the most cutting-edge public safety solution currently available in the market, emphasizing efficiency and collaboration in emergency management. Its dedication to innovation helps ensure that every department is equipped to meet the challenges of modern public safety effectively.