Heuristic AI

Created by team Heuristic AI on March 17, 2023

Heuristic AI brings browsing your Slack chat histories into a new dimension. Fueled by Qdrant vector search engine and the Generative model of Cohere, Heuristic.ai extracts the context from your question and matches it with your chat messages to elaborate the answer. Forget keywords and chats scrolling. We give you the answer and the source message in seconds! Vision: to enable people to find answers to any questions in their digital experience. Mission: to bring browsing chat histories to a new dimension How it works: 1. The user write normal query with the structure we have “hai, setup” or “hai, question” 2. Ngrok forward queries from slack_api to the Amazon server 3. Here, we evaluate the query to take action: - Setup from the sentence <hai, setup> or a sentence which contains hai and setup - Search: from the sentence that contains only the word hai - None, if the message sent in slack is a normal message 4. here we have two scenarios: - in the case of the setup action, we retrieve all the messages from all the channels, then encode them using co.embed prepare to be ready to store in Qdrant vector database - in the case of the search action, we encode the user query to retrieve the first 5 relevant messages from the conversations, then extract the answer to the user query from the first message retrieved using co.generate 5. Qdrant is the vectors search engine that allows us to store our vectors and to search on them. 6. Then lastly, the extracted answer is sent to the user.

Category tags:

Productivity, Knowledge Base, Virtual Assistant

Explore more applications

potato

Imagine a world where potatoes are more than just a starchy delight on your plate; they're the AI that replaces software engineers. Just like a potato's versatility in the culinary world, AI in software development can handle a myriad of tasks. These AI spuds can code, debug, and optimize software, making them indispensable in the tech industry. Much like a seasoned manager, they can oversee teams of virtual engineers, ensuring projects run smoothly. They adapt to different programming languages like a potato taking on various cooking styles. Whether you need a machine learning algorithm or a web application, these AI potatoes have got you covered. So, in this futuristic tech kitchen, the humble potato has transformed into a digital master chef, satisfying our software development cravings.

serg-v

OpenAI

AI-Comic-Factory

AI-Comic-Factory is a pioneering creative studio at the forefront of the comic book industry. Harnessing the power of cutting-edge technology, AI-Comic-Factory combines the precision of Falcon AI and the artistic finesse of SDXL (Superior Digital Xtreme Lineart) to revolutionize the way comics are produced. Our team of visionary artists, writers, and AI specialists collaborates seamlessly to bring captivating stories to life. With Falcon AI, we employ state-of-the-art natural language processing and image generation algorithms to craft engaging and immersive narratives. This ensures that every character, plot twist, and dialogue bubble resonates with readers on a profound level. The magic truly happens with SDXL, our proprietary technology for creating visually stunning comic art. SDXL elevates illustrations to a whole new level of detail and realism, pushing the boundaries of what's possible in the world of comic book aesthetics. Our artists leverage this tool to craft breathtaking visuals that complement the storytelling in unprecedented ways. AI-Comic-Factory isn't just about technology; it's about bringing imagination to life. We believe in the power of storytelling, and we're committed to pushing the boundaries of creativity using AI. Whether you're a comic enthusiast or a creator seeking to collaborate on the next big project, AI-Comic-Factory is your partner in bringing extraordinary comic experiences to the world. Explore the future of comics with us!

Team Tonic

FalconStable Diffusion

News-video generation

The code aims to solve the challenge of generating attention-grabbing headlines for news videos by harnessing the power of natural language processing and the Falcon-40b language model. Crafting compelling news headlines is essential for engaging viewers and conveying the essence of a news story effectively. However, manually creating these headlines can be time-consuming and creatively demanding. This solution automates the headline generation process, making it more efficient and potentially improving the quality of headlines. Falcon-Generated Headlines: The system generates attention-grabbing headlines using Falcon, a cutting-edge language model. These headlines are tailored to the news topic, ensuring relevance and viewer interest. Video Frame Generation: Python's MoviePy library is employed to transform these headlines into dynamic video frames. This step enhances the visual appeal of the news video while maintaining concise and informative content. Background Music Integration: To further captivate the audience, background music is seamlessly integrated into the video. The choice of music complements the news content, enhancing emotional resonance and viewer engagement. Efficiency and Speed: By automating headline generation and video frame creation, this solution significantly reduces the time and effort required for news video production. News agencies can produce content faster and stay ahead of breaking news. Increased Engagement: Short, visually appealing news videos with relevant headlines are more likely to grab viewers' attention. This leads to higher engagement, increased views, and improved viewer retention, driving growth for news agencies.

News-ai

Falcon

Neurolitiks Politics with Multi-AI Integration

NeuroLitiks is more than a digital tool; it's the future of political innovation. In today's world, city administrators are buried under immense data, desperately trying to identify the best path forward amidst a cloud of uncertainty. Enter Neurolitiks. Powered by state-of-the-art technologies like Expert.ia, OpenAI, Lang Chain, and Neo4j databases, our platform now integrates multiple machine learning models, including Llama 2 and Falcon, offering unparalleled analytics and insights. This fusion of technologies empowers us to discern vital information that might otherwise remain hidden or overwhelming. The rationale behind harnessing multiple AI systems? City management and policy-making are intricate, with countless interwoven threads. A singular analytical approach can't grasp this vastness. But our multi-AI setup, featuring Llama 2 and Falcon, can, facilitating a comprehensive, rounded understanding of city issues, allowing for pinpoint historical accuracy, real-time adaptability, and visionary future predictions. Initially targeting the health and education sectors in urban hubs—a $1.8 million slice of a more expansive $100 million market—Neurolitiks is not merely another digital system. It's a catalyst for monumental urban evolution. Our blend of superior databases and diverse AI models can process and decode complexity like no other, bestowing city leaders with the power to make data-driven, transformative decisions. Our mission goes beyond mere data interpretation; we aim to impart wisdom, transforming raw data into tangible strategies that can reshape city landscapes and improve the lives of their residents.

Hadox Human Networks

OpenAIClarifaiLlama 2LangChainFalcon
Streamlit
application badge

everdiver

Evernote is used by 250 million people worldwide to collect ideas, document meetings, and much more. It runs as a local application or in the cloud and has preceded comparable applications by the big tech companies. Once the note collection has grown over the years, it can become cumbersome to keep an overview and refer to past notes. Large language models offer help to improve search functions and build knowledge from old notes. With the dawn of open-source large language models such as Falcon by the Technology Innovation Institute, new possibilities have been opened. Since these models can be run on less powerful customer hardware, private Evernote data can now be processed, preserving privacy.

Fritzlabs

ClarifaiLangChainFalcon

"Really great idea and use of Qdrant vector search engine and Cohere's generative model. This tool has the potential to save a lot of time for Slack users who frequently search their chat histories, making it a valuable asset for businesses"

avatar

Theodoros Ampas

Co-Founder of Content-Hive

"Nice integration tool for tools validated with a high Total Addressable Market Size. Would love to see some further applications including a chat like feature within each of these tools to further ask questions and get context-specific answers "

avatar

Naman Parikh