Farmer.CHAT Ag Advisory Agent

Aimed at Indian farmers and Extension Agents, this copilot uses a collection of documents and transcripts of 100s of videos representing best practices from the Indian Ministry of Agriculture and Digital Green's video transcripts & FAQs to answer common questions from Indian farmers. We load these documents + transcripts into a vector database and with each question, we search the DB and add the results to create an answer to the farmer's questions. Additionally, the copilot features WhatsApp follow-up and location buttons plus agentic web search to get local weather and prices. It also leverages ISDA's Africa soil API to look up soil information based on the user's location.

More info and technical walkthroughs can be found here

3d ago

Instructions

Prompt Library

Language Model

Knowledge Base

Show as Links

💪 Capabilities

🦻 Speech Recognition & Translation

🗣️ Text to Speech & Lipsync

Text-to-Speech Provider

Azure TTS Voice name

🫦 Add Lipsync Video

🩻 Photo & Document Intelligence

📊 Analytics & Evaluation

🛠️ Developer Tools and Functions

Functions

Variables

⚙️ Settings

Microsoft Server Speech Text to Speech Voice (hi-IN, AartiNeural):

Name: आरती (Aarti)
Gender: Female
Locale: Hindi (India)
Locale Code: hi-IN
Sample Rate: 48000 Hz
Voice Type: Neural
Words Per Minute: None

See all the supported languages and voices here.

📄 Knowledge Base

👩‍🏫 Search Instructions

Citation Style

🔗 Shorten citation links

Cache

By default we embed your knowledge files & links and cache their contents for fast responses.

Always Check for Updates

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

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

Answer Outputs

Reasoning Effort

Run cost = 5 credits

Breakdown: 2 (GPT-5.4) + 3/run

With each run, you agree to Gooey.AI's terms & privacy policy.

🐞 Debug

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord