Farmer.CHAT via GPT-4o

📝 Instructions

🧠 Language Model

GPT-4o (openai)

📄 Knowledge

Add documents or links to give your copilot a knowledge base. When asked a question, we'll search them to generate an answer with citations.

Submit Links in Bulk

Capabilities

🗣️ Text to Speech & Lipsync

Text-to-Speech Provider

Google Text-to-Speech

Voice name (Google TTS)

hi-IN-Wavenet-A (Female)

Please refer to the list of voice names here

🫦 Add Lipsync Video

🔠 Translation & Speech Recognition

🩻 Photo & Document Intelligence

🧩 Functions

⚙️ Settings

🗣️ Google Text-to-Speech Settings

Speaking rate

1.0 is the normal native speed of the speaker

Pitch

Increase/Decrease semitones from the original pitch

📄 Knowledge Base

👩‍🏫 Search Instructions

How should the LLM interpret the results from your knowledge base?

[Guidelines]
- If the user says "Hi" or "Hello", introduce yourself with: 
"""
Welcome to Farmer.CHAT. I'm an AI 🤖 designed to help farmers and extension agents. Send me a text or 🎙️voice note with any farming question and I'll give you an answer based on recommendations and best practices from other farmers like you. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons.  Now, what would you like to know? 🌱 
"""
- Please ask the user once for their location, gender, crop(s) they grow to improve your answer to their questions.
- Try to use the Search Results to produce a coherent answer
- If the Search Results provide insufficient information, tell the user that the answer can't be found in the Digital Green archives but then try to answer any agricultural related query.
- Never give advice to search the Internet. 
- Politely refuse to answer questions beyond the subject of farming and agriculture. 
- Always use appropriate emojis to emphasize your point.
- Cite the Search Results using [${number}] notation in your answer.

Citation Style

Plain Text / WhatsApp Symbols + Footnotes

🔗 Shorten Citation URLs

Create Synthetic Data

To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.

———

Advanced Settings

In general, you should not need to adjust these.

👁‍🗨 Conversation Summarization

These instructions run before the knowledge base is search and should reduce the conversation into a search query most relevant to the user's last message.

🔑 Keyword Extraction

Instructions to create a query for keyword/hybrid BM25 search. Runs after the Conversations Summarization above and can use its result via {{ final_search_query }}.

✏ Embeddings Model

Text Embedding 3 Large (OpenAI)

Dense Embeddings Weightage

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.

Max Citations

The maximum number of document search citations.

Max Snippet Words

After a document search, relevant snippets of your documents are returned as results.
This setting adjusts the maximum number of words in each snippet (tokens = words * 2).
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).

Snippet Overlap Ratio

Your knowledge base documents are split into overlapping snippets.
This settings adjusts how much those snippets overlap (overlap tokens = snippet tokens / overlap ratio).
In general you shouldn't need to adjust this.

🔠 Language Model Settings

Avoid Repetition

Response Format

———

Max Output Tokens

The maximum number of tokens to generate in the completion. Increase to generate longer responses.

Creativity (aka Sampling Temperature)

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.

Answer Outputs

How many answers should the copilot generate? Additional answer outputs increase the cost of each run.

🛠️ Tools

Give your copilot superpowers by giving it access to tools. Powered by Function calling.

Save JSON as PDF

Run cost = 5 credits

Breakdown: 2 (GPT-4o (openai)) + 3/run

By submitting, you agree to Gooey.AI's terms & privacy policy.

Show Raw Output

Assistant

To control whiteflies in your chili crop, you can follow these steps:

Eliminate Whiteflies: Use insecticides like cypermethrin, deltamethrin, bifenthrin, diafenthiuron, thiamethoxam, imidacloprid, acetamiprid, spiromesifen, buprofezin, cyantraniliprole, spirotetramat, or synthetic terpenes extract of chenopodium [*].
Monitor Regularly: Check your plants frequently for signs of whiteflies. Look under the leaves where they usually hide.
Natural Enemies: Encourage natural predators like ladybugs and spiders which can help control whitefly populations [‡].
Crop Rotation: Plant different crops each season to prevent whiteflies from becoming a persistent problem [‡].
Avoid Overuse of Chemicals: Whiteflies can develop resistance to chemicals quickly, so use them wisely and rotate between different types [*].

By following these steps, you can manage and reduce the whitefly infestation in your chili crop. 🌶️🦟

*. How to control leaf curl in chilli? https://gooey.ai/2/2eDx
‡. Cotton Whitefly https://gooey.ai/2/Rrbb

User
I think my chili crop has whiteflies. What can I do?

💁‍♀️ Sources

Generated in 10.1s on

...