Groq compatibility? #136
Comments
|
For me adding the groq provider works. Example : |
Can't work on my nvim. |
|
@yuukibarns could you provide your gp configuration, outputs from Just be careful not to paste your secrets. |
|
The error msg is .html format which is hard to read, so i ignored it before. |
Why have I been blocked?This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solu tion. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data. |
|
And it told me that |
|
@yuukibarns the message is from ClaudFlare, can't provide more help without config and GpInspect data. |
{
"robitx/gp.nvim",
config = function()
local conf = {
providers = {
groq = {
disable = false,
endpoint = "https://api.groq.com/openai/v1/chat/completions",
secret = os.getenv("GROQ_API_KEY"),
},
openai = {
disable = true,
endpoint = "https://api.openai.com/v1/chat/completions",
-- secret = os.getenv("OPENAI_API_KEY"),
},
},
agents = {
{
name = "ChatGroqLlama3.1-70B",
provider = "groq",
chat = true,
command = false,
-- string with model name or table with model name and parameters
model = {
model = "llama-3.1-70b-versatile",
temperature = 0.6,
top_p = 1,
min_p = 0.05,
},
system_prompt = require("gp.defaults").chat_system_prompt,
},
{
name = "CodeGroqLlama3.1-70B",
provider = "groq",
chat = false,
command = true,
model = {
model = "llama-3.1-70b-versatile",
temperature = 0.4,
top_p = 1,
min_p = 0.05,
},
system_prompt = require("gp.defaults").code_system_prompt,
},
},
}
require("gp").setup(conf)
-- Setup shortcuts here (see Usage > Shortcuts in the Documentation/Readme)
end,
}, |
|
Plugin structure: |
|
|
|
@yuukibarns yep, sadly looks like a geo fence issue 🙁 https://github.com/groq/groq-python/issues/32 I've had similar troubles with gemini in EU, if you can get some proxy to fake your location to US you could use -- optional curl parameters (for proxy, etc.)
-- curl_params = { "--proxy", "http://X.X.X.X:XXXX" }
curl_params = {}, |
|
Thanks for your analysis. |
local env = require "env"
local OPENAI_KEY = env.OPENAI_KEY
local GROQ_KEY = env.GROQ_KEY
local OPENAI_HOST = "https://api.openai.com/v1/chat/completions"
local GROQ_HOST = "https://api.groq.com/openai/v1/chat/completions"
local GROQ_AUDIO = "https://api.groq.com/openai/v1/audio/transcriptions"
-- Gp (GPT prompt) lua plugin for Neovim
-- https://github.com/Robitx/gp.nvim/
--------------------------------------------------------------------------------
-- Default config
--------------------------------------------------------------------------------
---@class GpConfig
-- README_REFERENCE_MARKER_START
local config = {
providers = {
openai = {
disable = false,
endpoint = OPENAI_HOST,
secret = OPENAI_KEY,
},
groq = {
disable = false,
endpoint = GROQ_HOST,
secret = GROQ_KEY,
},
},
chat_shortcut_respond = { modes = { "n", "i", "v", "x" }, shortcut = "<C-g><cr>" },
chat_confirm_delete = false,
-- prefix for all commands
cmd_prefix = "Gp",
default_chat_agent = "GroqLLAMA_8B",
whisper = {
-- -- TODO: In the future, when gpnvim will support whisper options
-- endpoint = GROQ_AUDIO,
-- secret = GROQ_KEY,
},
agents = {
{
provider = "openai",
name = "ChatGPT4o",
chat = false,
command = true,
-- string with model name or table with model name and parameters
model = { model = "gpt-4o", temperature = 0.8, top_p = 1 },
-- system prompt (use this to specify the persona/role of the AI)
system_prompt = "You are an AI working as a code editor.\n\n"
.. "Please AVOID COMMENTARY OUTSIDE OF THE SNIPPET RESPONSE.\n"
.. "START AND END YOUR ANSWER WITH:\n\n```",
},
{
provider = "openai",
name = "ChatGPT4o-mini",
chat = true,
command = true,
-- string with model name or table with model name and parameters
model = { model = "gpt-4o-mini", temperature = 0.8, top_p = 1 },
-- system prompt (use this to specify the persona/role of the AI)
system_prompt = "You are an AI working as a code editor.\n\n"
.. "Please AVOID COMMENTARY OUTSIDE OF THE SNIPPET RESPONSE.\n"
.. "START AND END YOUR ANSWER WITH:\n\n```",
},
{
provider = "groq",
name = "GroqLLAMA_8B",
chat = true,
command = true,
-- string with model name or table with model name and parameters
model = { model = "llama-3.1-70b-versatile", temperature = 0.8, top_p = 1 },
system_prompt = "You are an AI helping the user with code and other tasks\n\n"
.. "Please AVOID COMMENTARY OUTSIDE OF THE SNIPPET RESPONSE.\n",
},
{
provider = "groq",
name = "GroqLLAMA_8B",
chat = true,
command = true,
-- string with model name or table with model name and parameters
model = { model = "llama-3.2-11b-text-preview", temperature = 0.8, top_p = 1 },
system_prompt = "Given a task or problem, please provide a concise and well-formatted solution or answer.\n\n"
.. "Please keep your response within a code snippet, and avoid unnecessary commentary.\n",
}
},
}
--
return {
"robitx/gp.nvim",
event = "BufEnter",
config = function() require("gp").setup(config) end,
}Oh, man. This plugin with Groq is just insane! Its very very fast. Makes it feel like a good Supermaven companion which is another tool I use. Note that |
Hi, I access
llama3-70bthrough groq using this python tool. I was hoping to also use groq with gp.nvim. Any plans to support this?The text was updated successfully, but these errors were encountered: