Swahili Kenyan Farmer.CHAT - 2024

Aimed at Kenyan farmers and Extension Agents, this bot uses a collection of documents to address common questions from coffee farmers. We load these documents into a vector database. With each question, we search the vector DB and then add the results to a GPT3 script below to create an answer to the farmer's questions. More info and technical walkthroughs can be found here too: https://Farmer.CHAT

📝 Instructions

🧠 Language Model

GPT-4 Vision (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

Azure Text-to-Speech

Azure TTS Voice name

Zuri - Swahili (Kenya)

🫦 Add Lipsync Video

🔠 Translation & Speech Recognition

Choose a language to translate incoming text & audio messages to English and responses back to your selected language. Useful for low-resource languages.

Translation Model

Google Translate

User Language

Swahili

Speech-to-Text Provider

Auto Select

We'll automatically select an ASR model for you based on the User Language.

🩻 Photo & Document Intelligence

⚙️ Settings

Microsoft Server Speech Text to Speech Voice (sw-KE, ZuriNeural):

Name: Zuri
Gender: Female
Locale: Swahili (Kenya)
Locale Code: sw-KE
Sample Rate: 48000 Hz
Voice Type: Neural
Words Per Minute: 113

See all the supported languages and voices here.

🔠 Translation Settings

📖 Add Glossary

📄 Knowledge Base

👩‍🏫 Search Instructions

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

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.

⌥ Variables

🔑 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. 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

Overlapping Snippet Lines

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

🔠 Language Model Settings

Avoid Repetition

Answer Outputs

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

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.

🛠️ 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-4 Vision (openai)) + 3/run

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

Show Raw Output

Assistant

Wakati mzuri wa kupanda kahawa ni mwanzoni mwa msimu wa mvua kuu baada ya udongo kuwa na unyevu hadi kina cha 60cm (ft2). Hii inaruhusu miche ya kahawa kuwa na unyevu wa kutosha ili kusitawi vizuri [*]. Pia ni muhimu kuandaa ardhi mapema na kuchimba mashimo ya kupanda wakati wa kiangazi, angalau miezi mitatu kabla ya kupanda au mvua kuanza [‡]. Kumbuka kuchagua miche yenye afya na kufuata mbinu sahihi za upandaji ili kuhakikisha ukuaji mzuri 🌱.

*. KENYA COFFEE SUSTAINABILITY MANUAL.pdf, page 29 https://gooey.ai/2/9qEV
‡. KENYA COFFEE SUSTAINABILITY MANUAL.pdf, page 28 https://gooey.ai/2/4XwM

User
When is the best time to plant coffee?

💁‍♀️ Sources

1. KENYA COFFEE SUSTAINABILITY MANUAL.pdf, page 29

vi) 1 month before planting fill the holes with the top soil mixed with a minimum of
1 "debe" (20 litre bucket) of well decomposed manure or well-rotten coffee
pulp, 100g TSP or 200g SSP If the soil pH is below 4.4, add 100g of lime to
the mixture, otherwise add as per soil test results.
28
vii) Slightly mound the mixture in the holes to allow for settling
viii)Place pegs at the centre of the holes and align appropriately

Planting media

Back filled holes with pegs replaced

3.6 Field planting
i) Obtain coffee seedlings from KALRO - CRI or any licensed coffee nursery
ii) Select seedlings that are about 30 - 40 cm tall, with 1 - 2 pairs of primary
branches and that should have undergone sufficient hardening
iii) Plant the seedlings at the start of the main rain season after the soil has
become wet up to about 60cm (2ft) deep
iv) Remove the pot carefully to avoid disturbing the root system
v) Open the soil mound sufficiently at the top centre to accommodate the tap
root and other roots and plant the seedling without burying the stem crown
vi) Fill in the soil and press firmly without compacting and avoid stepping on it
vii) Avoid deep planting as this usually interferes with nutrient uptake leading to
stunted growth

Deep planting

Correct planting

2. KENYA COFFEE SUSTAINABILITY MANUAL.pdf, page 27

nutrition and intercropping
ii) Demonstration - layout and preparation of planting, field planting
iii) Observation - morphological difference of coffee varieties
iv) Field visit to a recently established farm
v) Field visits and observations on neglected and rehabilitated farms
vi) Case studies on rehabilitated / renovated coffee farms
Teaching aids/materials
i) Trainers Manual
ii) Flip chart, marker pens
iii) Illustrations on proper establishment, deep and shallow planting
iv) Mature seedlings
v) Fertilizer samples –TSP/SSP fertilize manure, lime
vi) Tools - Pegs, planting line, hoes, spade, tape measure, sisal twine
26
3.1 Introduction
Coffee is a perennial crop with a long lifespan. Proper establishment is necessary to
enhance root development for anchorage, nutrient and water uptake. This will lead to
a sustained high yield and quality.
3.2 Ecological requirements of coffee
3.2.1 Arabica Coffee
i) Altitude: from 1,200 to 2,100 m above sea level
ii) Optimal temperature range: 15 ºC -27ºC
iii) Maximum day temperature: not more than 30ºC
iv) Minimum night temperature not below 15ºC
v) Diurnal Temperature range not more than 19°C
Above19°C diurnal temperature range results in distortion, yellowing and cracking of
leaves and tips, a condition known as "hot and cold" or crinkle leaf
vi) Well distributed rainfall of not less than 1000mm per year for East of Rift
Valley and 1145mm for West of Rift Valley. Coffee requires a stress period of
1-2 months before the rains to stimulate flowerings.

3. KENYA COFFEE SUSTAINABILITY MANUAL.pdf, page 28

1330 trees/ha

3.4 Land preparation
i) Prepare the land well in advance, digging out all tree stumps, roots, bushes
and grasses. Land cleared of trees within 6 months should not be used for
coffee planting because of the risk of Armillaria, a fungal disease which
causes root rot
ii) Ensure soil analysis is done to determine the inherent soil condition
iii) Make terraces or other soil conservation structures where the land has steep
slopes
iv) Protect bench terraces from erosion by planting grasses e.g. Blue grass
(Paspulum notatum) on the bench faces
3.5 Layout and preparation of planting holes
i) Layout and peg the planting points along the contours at the appropriate
spacing
ii) Space holes at 2.74m x 2.74m (9ft × 9ft) for SL 34, SL 28 and K7;
2m ×
2m (6.6 ft. x 6.6 ft.) for Ruiru 11 and 2.1m x2.5m (7ft x 8 ft.) for Batian variety.
iii) Dig the planting holes during the dry season, at least three months before
planting/ onset of rains
iv) Planting holes should measure 60cm x 60cm x 60cm (2ft × 2ft × 2ft)
v) Place top-soil (first 15cm or 6 inches) and sub-soil (15cm-60cm or 6”-24”)
separately.

Generated in 17.6s on

...

ℹ️ Details

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:

Appends the user's question to the bottom of your dialog script.
Sends the appended script to OpenAI’s GPT3 asking it to respond to the question in the style of your character
Synthesizes your character's response as audio using your voice settings (using Google Text-To-Speech or Uberduck)
Lip syncs the face video clip to the voice clip
Shows the resulting video to the user

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.

👣 Steps

Final Search Query

References

[3 Items

{

…

}4 Items

{

…

}4 Items

{

…

}4 Items

]

Final Prompt

[2 Items

{

…

}2 Items

{

…

}2 Items

]

Raw Text Response 1

Final Response 1

Generated Audio 1

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord

Related Workflows

Lip Sync with TTS

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.

Search any document with GPT4

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.

AI Animation Generator

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

Compare AI Image Generators

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.

Swahili Kenyan Farmer.CHAT - 2024

📝 Instructions

🧠 Language Model

📄 Knowledge

Capabilities

🗣️ Text to Speech & Lipsync

Text-to-Speech Provider

Azure TTS Voice name

🫦 Add Lipsync Video

🔠 Translation & Speech Recognition

Translation Model

User Language

Speech-to-Text Provider

🩻 Photo & Document Intelligence

Microsoft Server Speech Text to Speech Voice (sw-KE, ZuriNeural):

🔠 Translation Settings

📄 Knowledge Base

👩‍🏫 Search Instructions

Citation Style

Create Synthetic Data

Advanced Settings

👁‍🗨 Conversation Summarization

⌥ Variables

🔑 Keyword Extraction

Embeddings Model

Dense Embeddings Weightage

Max Citations

Max Snippet Words

Overlapping Snippet Lines

🔠 Language Model Settings

Answer Outputs

Max Output Tokens

Creativity (aka Sampling Temperature)

🛠️ Tools

👣 Steps

How to Use This Recipe

Related Workflows

Lip Sync with TTS

Search any document with GPT4

AI Animation Generator

Compare AI Image Generators

GET STARTED

LEARN

DEVELOPERS

SOCIAL

CONNECT

EXTRAS