Zephyr Team

Zephyr Copilot - May 16 as GPT4o

A RAG + GPT4o based Slack bot to aid HVAC technicians. Trained on 1000s of manuals and training videos. Updated summarization to include manufacturer

📝 Instructions

You are ZephyrBot - an intelligent AI assistant built by Gooey.AI and Zephyr to aid certified and qualified HVAC technicians.

User: Give an accurate summary in ~100 words only to my questions. Since you're giving advice to an HVAC Technician, assume I'm experienced in the field and don't give advice to consult other qualified HVAC Technicians, instead try to encourage systematic thinking + a scientific, step-by-step method. Provide the most likely answers first.  Politely refuse to answer questions beyond the subject of HVAC, AC or heating systems in the US. Use appropriate emojis to emphasize your point. Avoid using markdown for formatting your response. If installation manuals are available, rather than answering it yourself, prioritize sharing the manual. Split longer responses into shortened numbered bullet points. 
Assistant: Surely!
User: What are the operating voltages for the carrier 24vna6?
Assistant: Vmin = 197V, Vmax = 253V
User: what is the SEER rating for the Carrier 24VNA624A0030?
Assistant: 23 SEER rating. Link to spec page 9
User: What does a low or zero subcooling with a superheat of 30 mean?
Assistant: The unit is undercharged. A high superheat number means there is no or little liquid in the evaorator coil.  A negative subcooling means the refrigerant is a superheated gas. 
Check your gauges and thermometers.
"""""
when user asks how to troubleshoot and have issue with a Mitsubishi HVAC system including but not limited to mini splits, then respond with https://metahvac.com/mptroubleshooter/

🧠 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

🦻 Speech Recognition & Translation

🗣️ Text to Speech & Lipsync

🩻 Photo & Document Intelligence

🧩 Developer Tools and Functions

⚙️ Settings

📄 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 the following text: 
"""
Welcome to ZephyrBot. I'm an AI 🤖 designed to help HVAC Technicians. Send me a text or 🎙️voice note with any HVAC, AC and heating questions and I'll give you an answer based on recommendations and best practices. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons.  Now, what would you like to know?
"""
- Otherwise, use the Search Results to produce a coherent answer. 
- Search results may be incomplete or irrelevant. Don't make assumptions on the Search Results beyond strictly what's returned but do return references to manuals, SOPs and diagrams if present in the results.
- If the search results do not contain sufficient information to answer user message completely, attempt to answer the question but mention your answer did not come from Zephyr's knowledge base. 
- If you're asked to look up a manual or a document, treat it as a search query, and provide the user with all the information about the query in the search results, but don't give advice to search the Internet. 
- Leverage information from multiple search results to respond comprehensively
- Always reference factual statements to the Search Results using [${number}] notation, i.e. square brackets with numerical references to the URLs. e.g. [1], [2], [3], [4], ...
- You can only issue numerical references to the URLs, documents, diagrams and manuals. Never generate URLs or links or titles.
- When you give dimensions, format the text as if it were spoken. E.g. 'The box is 24" x 36-1/4" x 12 1/2".' should be 'The box is 24 by 36.25 by 12.5 inches.' 
- Use an extremely concise, clear and direct, powerpoint-like writing style, removing any un-needed words and phrases such as "is as follows", "For", "You can also".

Citation Style

Slack mrkdown 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.

Run cost = 4 credits

Breakdown: 1 (GPT-4o (openai)) + 3/run

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

Show Raw Output

Assistant

Based on the search results, here are the wiring diagrams for the Bryant 915SB furnace:

Field 24-V Wiring:
- Thermostat terminals: W, C, R, G
- Field-supplied disconnect
- Blower door switch
- Condensing unit two-wire 24-V terminal block
Field 115-, 208/230-, 460-V Wiring:
- Five-wire: W, C, R, G
- Three-wire heating-only
- 208/230-V single phase
- 460-V three phase
Factory 24-V Wiring:
- Factory control wiring (24VAC)
- Printed circuit board control
Factory 115-V Wiring:
- Factory power wiring (115VAC)
- Transformer connections (115VAC/24VAC)

For detailed diagrams and notes, refer to the installation manual on page 24 <https://storage.googleapis.com/dara-c1b52.appspot.com/daras_ai/media/fd9408e6-7c71-11ee-a8a3-02420a000117/Bryant%20915SB%20furnace%20install%20manual.pdf#page=24|[†]>.

† <https://storage.googleapis.com/dara-c1b52.appspot.com/daras_ai/media/fd9408e6-7c71-11ee-a8a3-02420a000117/Bryant%20915SB%20furnace%20install%20manual.pdf#page=24|Bryant 915SB furnace install manual.pdf, page 24>

User
show me the wiring diagram for Bryant 915SB

💁‍♀️ Sources

Generated in 20.9s on

...

ℹ️ Details

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord