Aimed at Indian farmers and frontline, this bot uses a collection of documents, manuals and & FAQs to answer common questions from Indian farmers and frontline workers.
High-level system instructions to the copilot + optional example conversations between the bot and the user.
Upload documents or enter URLs to give your copilot a knowledge base. With each incoming user message, we'll search your documents via a vector DB query.
Enter Custom URLs
Guidelines to interpret the results of the knowledge base query.
🔗 Shorten Citation URLs
Shorten citation links and enable click tracking of knowledge base URLs, docs, PDF and/or videos.
Prompt to transform the conversation history into a vector search query.These instructions run before the workflow performs a search of the knowledge base documents and should summarize the conversation into a VectorDB query most relevant to the user's last message. In general, you shouldn't need to adjust these instructions.
Weightage for dense vs sparse embeddings. 0 for sparse, 1 for dense, 0.5 for equal weight.
Generally speaking, dense embeddings excel at understanding the context of the query, whereas sparse vectors excel at keyword matches.
The maximum number of document search citations.
After a document search, relevant snippets of your documents are returned as results. This setting adjusts the maximum number of words in each snippet. A high snippet size allows the LLM to access more information from your document results, at the cost of being verbose and potentially exhausting input tokens (which can cause a failure of the copilot to respond). Default: 300
Your knowledge base documents are split into overlapping snippets. This settings adjusts how much those snippets overlap. In general you shouldn't need to adjust this. Default: 5
When your copilot users upload a photo or pdf, what kind of document are they mostly likely to upload? (via Azure)
How many answers should the copilot generate? Additional answer outputs increase the cost of each run.
The maximum number of tokens to generate in the completion. Increase to generate longer responses.
Higher values allow the LLM to take more risks. Try values larger than 1 for more creative applications or 0 to ensure that LLM gives the same answer when given the same user input.
If provided, the copilot will translate user messages to English and the copilot's response back to the selected language.
Provide a glossary to customize translation and improve accuracy of domain-specific terms.
If not specified or invalid, no glossary will be used. Read about the expected format here.
Translation Glossary for User Langauge -> LLM Language (English)
Translation Glossary for LLM Language (English) -> User Langauge
Enable Audio Output?
Google Cloud Text-to-Speech
Please refer to the list of voice names here
1.0 is the normal native speed of the speaker
Increase/Decrease semitones from the original pitch
Enable Video Output?
Run cost = 5 credits
Success! Run Time: 5.38 seconds.
Show Raw Output
Neemastra can be stored in plastic drums. It has a shelf life of about 3 months  .
UserHow to store neemastra?
1. Technical manual -FINAL FINAL- copy copy copy.pdf, page 30
2. Technical manual -FINAL FINAL- copy copy copy.pdf, page 32
3. Technical manual -FINAL FINAL- copy copy copy.pdf, page 41
4. Technical manual -FINAL FINAL- copy copy copy.pdf, page 33
5. Technical manual -FINAL FINAL- copy copy copy.pdf, page 53
Have you ever wanted to create a bot that you could talk to about anything? Ever wanted to create your own https://dara.network/RadBots or https://Farmer.CHAT? This is how.
This workflow takes a dialog LLM prompt describing your character, a collection of docs & links and optional an video clip of your bot’s face and voice settings.
We use all these to build a bot that anyone can speak to about anything and you can host directly in your own site or app, or simply connect to your Facebook, WhatsApp or Instagram page.
How It Works:
PS. This is the workflow that we used to create RadBots - a collection of Turing-test videobots, authored by leading international writers, singers and playwrights - and really inspired us to create Gooey.AI so that every person and organization could create their own fantastic characters, in any personality of their choosing. It's also the workflow that powers https://Farmer.CHAT and was demo'd at the UN General Assembly in April 2023 as a multi-lingual WhatsApp bot for Indian, Ethiopian and Kenyan farmers.
Final Search Query
Raw Text Response 1
Final Response 1
Generated Audio 1
🙋🏽♀️ Need more help? Join our Discord
Add your text prompt, pick a voice & upload a sample video to quickly create realistic lipsync videos. Discover the ease of text-to-video AI.
Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with a GPT3 script. This workflow is perfect for anything NOT in ChatGPT: 250-page compliance PDFs, training manuals, your diary, etc.
Create AI-generated Animation without relying on complex CoLab notebooks. Input your prompts + keyframes and bring your ideas to life using the animation capabilities of Gooey & Stable Diffusion's Deforum. For more help on how to use the tool visit https://www.help.gooey.ai/learn-animation
Create multiple AI photos from one prompt using Stable Diffusion (1.5 -> 2.1, Open/Midjourney), DallE, and other models. Find out which AI Image generator works best for your text prompt on comparing OpenAI, Stability.AI etc.
©2023 by Gooey.AI / Dara.network Inc