Neovim Hax

Guide to help with Neovim use

📝 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

🔠 Translation & Speech Recognition

🩻 Photo & Document Intelligence

🧩 Developer Tools and Functions

⌥ Variables

Variables let you pass custom parameters to your workflow. Access a variable in your instruction prompt with Jinja, e.g. {{ my_variable }}
Learn more.

platform

⚙️ Settings

📄 Knowledge Base

👩‍🏫 Search Instructions

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

Citation Style

Numbers ( [1] [2] [3] ..)

🔗 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

To select text inside brackets in Vim or Neovim, you can use the vi( command.

Here's how it works:

v: Enter Visual mode to start selecting text.
i: Stands for "inner", which is used to specify the text object.
(: This specifies the type of text object to select, in this case, everything inside the parentheses. Similarly, you can use { for curly braces or [ for square brackets.

For example, if your cursor is inside the brackets of a text like (example text), using vi( will select example text without the parentheses.

User
How to select text inside brackets?

Assistant
:q

To quit Vim, you can use the command :q in normal mode. This will exit Vim as long as there are no unsaved changes to the file you are editing. If there are unsaved changes and you still want to quit without saving, you can use :q!. If you want to save changes and then quit, you can use :wq.

User
How to quit Vim?

💁‍♀️ Sources

Generated in 6.5s on

...

ℹ️ Details

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord