IFFCO Chat - Mar 13

Aimed at Indian farmers and Extension Agents, this bot uses a collection of documents and transcripts of 100s of videos representing best practices to answer common questions from Indian farmers. We load these documents + transcripts into a vector database. With each question, we search the vector DB and then add the results to a GPT script below to create an answer to the farmer's questions. Chat on WhatsApp here: http://wa.me/+12069293178.

2y ago

Instructions

Prompt Library

Language Model

Knowledge Base

Show as Links

💪 Capabilities

🦻 Speech Recognition & Translation

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

Filter by Language

Speech-to-Text Provider

Spoken Language

🔠 Translate to & from English

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

Use Whisper Large v2 (openai) for speech translation from Detected Language to English

Translation Model

Translation Language

🗣️ Text to Speech & Lipsync

Text-to-Speech Provider

Voice name (Google TTS)

Please refer to the list of voice names here

🫦 Add Lipsync Video

🩻 Photo & Document Intelligence

📊 Analytics & Evaluation

🛠️ Developer Tools and 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

🔠 Translation Settings

📖 Add Glossary

📄 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

Creativity (aka Sampling Temperature)

Answer Outputs

Run cost = 5 credits

Breakdown: 3 (GPT-4 Vision • openai [Redirects to GPT-4o]) + 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