chore: add google gemini and deepseek as new supported remote engine providers (#4596)
* chore: add google gemini and deepseek as new supported remote engine providers * chore: add logos * chore: fallback default error message on empty * chore: update open router models * chore: typo fix * chore: remove unusable queen vl
This commit is contained in:
Louis
GitHub
parent
ca220d18a6
commit
a87bbd2840
@ -6,6 +6,8 @@ import groq from './resources/groq.json' with { type: 'json' }
|
||||
import martian from './resources/martian.json' with { type: 'json' }
|
||||
import mistral from './resources/mistral.json' with { type: 'json' }
|
||||
import nvidia from './resources/nvidia.json' with { type: 'json' }
|
||||
import deepseek from './resources/deepseek.json' with { type: 'json' }
|
||||
import googleGemini from './resources/google_gemini.json' with { type: 'json' }
|
||||
|
||||
import anthropicModels from './models/anthropic.json' with { type: 'json' }
|
||||
import cohereModels from './models/cohere.json' with { type: 'json' }
|
||||
@ -15,6 +17,8 @@ import groqModels from './models/groq.json' with { type: 'json' }
|
||||
import martianModels from './models/martian.json' with { type: 'json' }
|
||||
import mistralModels from './models/mistral.json' with { type: 'json' }
|
||||
import nvidiaModels from './models/nvidia.json' with { type: 'json' }
|
||||
import deepseekModels from './models/deepseek.json' with { type: 'json' }
|
||||
import googleGeminiModels from './models/google_gemini.json' with { type: 'json' }
|
||||
|
||||
const engines = [
|
||||
anthropic,
|
||||
@ -25,6 +29,8 @@ const engines = [
|
||||
mistral,
|
||||
martian,
|
||||
nvidia,
|
||||
deepseek,
|
||||
googleGemini,
|
||||
]
|
||||
const models = [
|
||||
...anthropicModels,
|
||||
@ -35,5 +41,7 @@ const models = [
|
||||
...mistralModels,
|
||||
...martianModels,
|
||||
...nvidiaModels,
|
||||
...deepseekModels,
|
||||
...googleGeminiModels,
|
||||
]
|
||||
export { engines, models }
|
||||
|
||||
28
extensions/engine-management-extension/models/deepseek.json
Normal file
28
extensions/engine-management-extension/models/deepseek.json
Normal file
@ -0,0 +1,28 @@
|
||||
[
|
||||
{
|
||||
"model": "deepseek-chat",
|
||||
"object": "model",
|
||||
"name": "DeepSeek Chat",
|
||||
"version": "1.0",
|
||||
"description": "The deepseek-chat model has been upgraded to DeepSeek-V3. deepseek-reasoner points to the new model DeepSeek-R1",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "deepseek"
|
||||
},
|
||||
{
|
||||
"model": "deepseek-reasoner",
|
||||
"object": "model",
|
||||
"name": "DeepSeek R1",
|
||||
"version": "1.0",
|
||||
"description": "CoT (Chain of Thought) is the reasoning content deepseek-reasoner gives before output the final answer. For details, please refer to Reasoning Model.",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "deepseek"
|
||||
}
|
||||
]
|
||||
@ -0,0 +1,67 @@
|
||||
[
|
||||
{
|
||||
"model": "gemini-2.0-flash",
|
||||
"object": "model",
|
||||
"name": "Gemini 2.0 Flash",
|
||||
"version": "1.0",
|
||||
"description": "Gemini 2.0 Flash delivers next-gen features and improved capabilities, including superior speed, native tool use, multimodal generation, and a 1M token context window.",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "google_gemini"
|
||||
},
|
||||
{
|
||||
"model": "gemini-2.0-flash-lite-preview",
|
||||
"object": "model",
|
||||
"name": "Gemini 2.0 Flash-Lite Preview",
|
||||
"version": "1.0",
|
||||
"description": "A Gemini 2.0 Flash model optimized for cost efficiency and low latency.",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "google_gemini"
|
||||
},
|
||||
{
|
||||
"model": "gemini-1.5-flash",
|
||||
"object": "model",
|
||||
"name": "Gemini 1.5 Flash",
|
||||
"version": "1.0",
|
||||
"description": "Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks.",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "google_gemini"
|
||||
},
|
||||
{
|
||||
"model": "gemini-1.5-flash-8b",
|
||||
"object": "model",
|
||||
"name": "Gemini 1.5 Flash-8B",
|
||||
"version": "1.0",
|
||||
"description": "Gemini 1.5 Flash-8B is a small model designed for lower intelligence tasks.",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "google_gemini"
|
||||
},
|
||||
{
|
||||
"model": "gemini-1.5-pro",
|
||||
"object": "model",
|
||||
"name": "Gemini 1.5 Pro",
|
||||
"version": "1.0",
|
||||
"description": "Gemini 1.5 Pro is a mid-size multimodal model that is optimized for a wide-range of reasoning tasks. 1.5 Pro can process large amounts of data at once, including 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages of text. ",
|
||||
"inference_params": {
|
||||
"max_tokens": 8192,
|
||||
"temperature": 0.6,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "google_gemini"
|
||||
}
|
||||
]
|
||||
@ -82,7 +82,6 @@
|
||||
"max_tokens": 100000,
|
||||
"temperature": 1,
|
||||
"top_p": 1,
|
||||
"stream": true,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0
|
||||
},
|
||||
|
||||
@ -1,16 +1,61 @@
|
||||
[
|
||||
{
|
||||
"model": "open-router-auto",
|
||||
"model": "deepseek/deepseek-r1:free",
|
||||
"object": "model",
|
||||
"name": "OpenRouter",
|
||||
"name": "DeepSeek: R1",
|
||||
"version": "1.0",
|
||||
"description": " OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them.",
|
||||
"description": "OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them.",
|
||||
"inference_params": {
|
||||
"max_tokens": 128000,
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0
|
||||
"presence_penalty": 0,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "openrouter"
|
||||
},
|
||||
{
|
||||
"model": "deepseek/deepseek-r1-distill-llama-70b:free",
|
||||
"object": "model",
|
||||
"name": "DeepSeek: R1 Distill Llama 70B",
|
||||
"version": "1.0",
|
||||
"description": " OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them.",
|
||||
"inference_params": {
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "openrouter"
|
||||
},
|
||||
{
|
||||
"model": "deepseek/deepseek-r1-distill-llama-70b:free",
|
||||
"object": "model",
|
||||
"name": "DeepSeek: R1 Distill Llama 70B",
|
||||
"version": "1.0",
|
||||
"description": "OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them.",
|
||||
"inference_params": {
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "openrouter"
|
||||
},
|
||||
{
|
||||
"model": "meta-llama/llama-3.1-405b-instruct:free",
|
||||
"object": "model",
|
||||
"name": "Meta: Llama 3.1 405B Instruct",
|
||||
"version": "1.0",
|
||||
"description": "OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them.",
|
||||
"inference_params": {
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"stream": true
|
||||
},
|
||||
"engine": "openrouter"
|
||||
}
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-anthropic-extension",
|
||||
"id": "anthropic",
|
||||
"type": "remote",
|
||||
"engine": "anthropic",
|
||||
"url": "https://console.anthropic.com/settings/keys",
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-cohere-extension",
|
||||
"id": "cohere",
|
||||
"type": "remote",
|
||||
"engine": "cohere",
|
||||
"url": "https://dashboard.cohere.com/api-keys",
|
||||
|
||||
@ -0,0 +1,23 @@
|
||||
{
|
||||
"id": "deepseek",
|
||||
"type": "remote",
|
||||
"engine": "deepseek",
|
||||
"url": "https://platform.deepseek.com/api_keys",
|
||||
"api_key": "",
|
||||
"metadata": {
|
||||
"get_models_url": "https://api.deepseek.com/models",
|
||||
"header_template": "Authorization: Bearer {{api_key}}",
|
||||
"transform_req": {
|
||||
"chat_completions": {
|
||||
"url": "https://api.deepseek.com/chat/completions",
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"messages\" or key == \"temperature\" or key == \"store\" or key == \"max_tokens\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"model\" or key == \"seed\" or key == \"stop\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"transform_resp": {
|
||||
"chat_completions": {
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"choices\" or key == \"created\" or key == \"model\" or key == \"service_tier\" or key == \"system_fingerprint\" or key == \"stream\" or key == \"object\" or key == \"usage\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"explore_models_url": "https://api-docs.deepseek.com/quick_start/pricing"
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,23 @@
|
||||
{
|
||||
"id": "google_gemini",
|
||||
"type": "remote",
|
||||
"engine": "google_gemini",
|
||||
"url": "https://aistudio.google.com/apikey",
|
||||
"api_key": "",
|
||||
"metadata": {
|
||||
"get_models_url": "https://generativelanguage.googleapis.com/v1beta/models",
|
||||
"header_template": "Authorization: Bearer {{api_key}}",
|
||||
"transform_req": {
|
||||
"chat_completions": {
|
||||
"url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"messages\" or key == \"temperature\" or key == \"store\" or key == \"max_tokens\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"model\" or key == \"seed\" or key == \"stop\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"transform_resp": {
|
||||
"chat_completions": {
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"choices\" or key == \"created\" or key == \"model\" or key == \"service_tier\" or key == \"system_fingerprint\" or key == \"stream\" or key == \"object\" or key == \"usage\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"explore_models_url": "https://ai.google.dev/gemini-api/docs/models/gemini"
|
||||
}
|
||||
}
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-groq-extension",
|
||||
"id": "groq",
|
||||
"type": "remote",
|
||||
"engine": "groq",
|
||||
"url": "https://console.groq.com/keys",
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-martian-extension",
|
||||
"id": "martian",
|
||||
"type": "remote",
|
||||
"engine": "martian",
|
||||
"url": "https://withmartian.com/dashboard",
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-mistral-extension",
|
||||
"id": "mistral",
|
||||
"type": "remote",
|
||||
"engine": "mistral",
|
||||
"url": "https://console.mistral.ai/api-keys/",
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-nvidia-extension",
|
||||
"id": "nvidia",
|
||||
"type": "remote",
|
||||
"engine": "nvidia",
|
||||
"url": "https://org.ngc.nvidia.com/setup/personal-keys",
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-openai-extension",
|
||||
"id": "openai",
|
||||
"type": "remote",
|
||||
"engine": "openai",
|
||||
"url": "https://platform.openai.com/account/api-keys",
|
||||
@ -10,7 +10,7 @@
|
||||
"transform_req": {
|
||||
"chat_completions": {
|
||||
"url": "https://api.openai.com/v1/chat/completions",
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"model\" or key == \"temperature\" or key == \"store\" or key == \"messages\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"seed\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" or key == \"max_tokens\" or ((input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\" or input_request.model == \"o3\" or input_request.model == \"o3-mini\") and (key == \"stop\")) %} {% if not first %} , {% endif %} {% if key == \"messages\" and (input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\") and input_request.messages.0.role == \"system\" %} \"messages\": [{% for message in input_request.messages %} {% if not loop.is_first %} { \"role\": \"{{ message.role }}\", \"content\": \"{{ message.content }}\" } {% if not loop.is_last %} , {% endif %} {% endif %} {% endfor %}] {% else if key == \"max_tokens\" and (input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\" or input_request.model == \"o3\" or input_request.model == \"o3-mini\") %} \"max_completion_tokens\": {{ tojson(value) }} {% else %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endif %} {% endfor %} }"
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"model\" or key == \"temperature\" or key == \"store\" or key == \"messages\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"seed\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" or key == \"max_tokens\" or ((input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\" or input_request.model == \"o3\" or input_request.model == \"o3-mini\") and (key == \"stop\")) %} {% if not first %} , {% endif %} {% if key == \"messages\" and (input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\") and input_request.messages.0.role == \"system\" %} \"messages\": [{% for message in input_request.messages %} {% if not loop.is_first %} { \"role\": \"{{ message.role }}\", \"content\": \"{{ message.content }}\" } {% if not loop.is_last %} , {% endif %} {% endif %} {% endfor %}] {% else if key == \"max_tokens\" and (input_request.model == \"o1\" or input_request.model == \"o1-preview\" or input_request.model == \"o1-mini\" or input_request.model == \"o3\" or input_request.model == \"o3-mini\") %} \"max_completion_tokens\": {{ tojson(value) }} {% set first = false %} {% else %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"transform_resp": {
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
{
|
||||
"id": "@janhq/inference-openrouter-extension",
|
||||
"id": "openrouter",
|
||||
"type": "remote",
|
||||
"engine": "openrouter",
|
||||
"url": "https://openrouter.ai/keys",
|
||||
@ -10,7 +10,7 @@
|
||||
"transform_req": {
|
||||
"chat_completions": {
|
||||
"url": "https://openrouter.ai/api/v1/chat/completions",
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"messages\" or key == \"temperature\" or key == \"store\" or key == \"max_tokens\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"seed\" or key == \"stop\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
"template": "{ {% set first = true %} {% for key, value in input_request %} {% if key == \"messages\" or key == \"temperature\" or key == \"store\" or key == \"max_tokens\" or key == \"stream\" or key == \"presence_penalty\" or key == \"metadata\" or key == \"frequency_penalty\" or key == \"tools\" or key == \"tool_choice\" or key == \"logprobs\" or key == \"top_logprobs\" or key == \"logit_bias\" or key == \"n\" or key == \"modalities\" or key == \"prediction\" or key == \"response_format\" or key == \"service_tier\" or key == \"model\" or key == \"seed\" or key == \"stop\" or key == \"stream_options\" or key == \"top_p\" or key == \"parallel_tool_calls\" or key == \"user\" %} {% if not first %},{% endif %} \"{{ key }}\": {{ tojson(value) }} {% set first = false %} {% endif %} {% endfor %} }"
|
||||
}
|
||||
},
|
||||
"transform_resp": {
|
||||
|
||||
@ -89,6 +89,9 @@ const ErrorMessage = ({ message }: { message: ThreadMessage }) => {
|
||||
{message?.content[0]?.text?.value && (
|
||||
<AutoLink text={message?.content[0]?.text?.value} />
|
||||
)}
|
||||
{!message?.content[0]?.text?.value && (
|
||||
<span>Something went wrong. Please try again.</span>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</p>
|
||||
|
||||
@ -42,7 +42,7 @@ import useUpdateModelParameters from '@/hooks/useUpdateModelParameters'
|
||||
import { formatDownloadPercentage, toGibibytes } from '@/utils/converter'
|
||||
|
||||
import { manualRecommendationModel } from '@/utils/model'
|
||||
import { getLogoEngine } from '@/utils/modelEngine'
|
||||
import { getLogoEngine, getTitleByEngine } from '@/utils/modelEngine'
|
||||
|
||||
import { activeAssistantAtom } from '@/helpers/atoms/Assistant.atom'
|
||||
import {
|
||||
@ -252,18 +252,13 @@ const ModelDropdown = ({
|
||||
],
|
||||
})
|
||||
|
||||
const defaultContextLength = Math.min(
|
||||
8192,
|
||||
model?.settings.ctx_len ?? 8192
|
||||
)
|
||||
|
||||
const contextLength = model?.settings.ctx_len
|
||||
? Math.min(8192, model?.settings.ctx_len ?? 8192)
|
||||
: undefined
|
||||
const overriddenParameters = {
|
||||
ctx_len: model?.settings.ctx_len ? defaultContextLength : undefined,
|
||||
max_tokens: defaultContextLength
|
||||
? Math.min(
|
||||
model?.parameters.max_tokens ?? 8192,
|
||||
defaultContextLength
|
||||
)
|
||||
ctx_len: contextLength,
|
||||
max_tokens: contextLength
|
||||
? Math.min(model?.parameters.max_tokens ?? 8192, contextLength)
|
||||
: model?.parameters.max_tokens,
|
||||
}
|
||||
|
||||
@ -434,7 +429,7 @@ const ModelDropdown = ({
|
||||
/>
|
||||
)}
|
||||
<h6 className="font-medium capitalize text-[hsla(var(--text-secondary))]">
|
||||
{engine.name}
|
||||
{getTitleByEngine(engine.name)}
|
||||
</h6>
|
||||
</div>
|
||||
<div className="-mr-2 flex gap-1">
|
||||
|
||||
@ -82,24 +82,18 @@ export const useCreateNewThread = () => {
|
||||
}
|
||||
|
||||
// Default context length is 8192
|
||||
const defaultContextLength = Math.min(
|
||||
8192,
|
||||
defaultModel?.settings?.ctx_len ?? 8192
|
||||
)
|
||||
const contextLength = defaultModel?.settings?.ctx_len
|
||||
? Math.min(8192, defaultModel?.settings?.ctx_len)
|
||||
: undefined
|
||||
|
||||
const overriddenSettings = {
|
||||
ctx_len: defaultModel?.settings?.ctx_len
|
||||
? Math.min(8192, defaultModel?.settings?.ctx_len)
|
||||
: undefined,
|
||||
ctx_len: contextLength,
|
||||
}
|
||||
|
||||
// Use ctx length by default
|
||||
const overriddenParameters = {
|
||||
max_tokens: defaultContextLength
|
||||
? Math.min(
|
||||
defaultModel?.parameters?.max_tokens ?? 8192,
|
||||
defaultContextLength
|
||||
)
|
||||
max_tokens: contextLength
|
||||
? Math.min(defaultModel?.parameters?.max_tokens ?? 8192, contextLength)
|
||||
: defaultModel?.parameters?.max_tokens,
|
||||
}
|
||||
|
||||
|
||||
@ -196,7 +196,10 @@ export default function useSendChatMessage() {
|
||||
}
|
||||
updateThread(updatedThread)
|
||||
|
||||
if (!isResend) {
|
||||
if (
|
||||
!isResend &&
|
||||
(newMessage.content.length || newMessage.attachments?.length)
|
||||
) {
|
||||
// Add message
|
||||
const createdMessage = await extensionManager
|
||||
.get<ConversationalExtension>(ExtensionTypeEnum.Conversational)
|
||||
|
||||
25
web/public/images/ModelProvider/deepseek.svg
Normal file
25
web/public/images/ModelProvider/deepseek.svg
Normal file
@ -0,0 +1,25 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 25.4.1, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
|
||||
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
|
||||
viewBox="0 0 56.2 41.4" style="enable-background:new 0 0 56.2 41.4;" xml:space="preserve">
|
||||
<style type="text/css">
|
||||
.st0{fill:#4D6BFE;}
|
||||
</style>
|
||||
<desc>Created with Pixso.</desc>
|
||||
<path id="path_00000023980838171174838950000018388351879808150157_" class="st0" d="M55.6,3.5C55,3.2,54.8,3.7,54.4,4
|
||||
c-0.1,0.1-0.2,0.2-0.3,0.3c-0.9,0.9-1.9,1.5-3.2,1.5c-1.9-0.1-3.6,0.5-5.1,2c-0.3-1.8-1.3-2.9-2.9-3.6c-0.8-0.4-1.7-0.7-2.2-1.5
|
||||
c-0.4-0.6-0.5-1.2-0.7-1.8c-0.1-0.4-0.3-0.8-0.7-0.8c-0.5-0.1-0.7,0.3-0.8,0.6c-0.7,1.3-1,2.8-1,4.3c0.1,3.4,1.5,6,4.3,7.9
|
||||
c0.3,0.2,0.4,0.4,0.3,0.8c-0.2,0.7-0.4,1.3-0.6,1.9c-0.1,0.4-0.3,0.5-0.8,0.3c-1.5-0.6-2.9-1.6-4.1-2.8c-2-1.9-3.8-4.1-6.1-5.8
|
||||
C30,7,29.4,6.7,28.9,6.3c-2.3-2.2,0.3-4.1,0.9-4.3C30.4,1.8,30,1,28,1c-2,0-3.9,0.7-6.3,1.6c-0.3,0.1-0.7,0.2-1.1,0.3
|
||||
c-2.2-0.4-4.4-0.5-6.8-0.2C9.4,3.2,5.9,5.3,3.3,8.8C0.2,13.1-0.5,18,0.4,23.1c0.9,5.3,3.7,9.8,7.9,13.2c4.4,3.6,9.4,5.3,15.1,5
|
||||
c3.5-0.2,7.3-0.7,11.7-4.4c1.1,0.5,2.3,0.8,4.2,0.9c1.5,0.1,2.9-0.1,4-0.3c1.7-0.4,1.6-2,1-2.3c-5-2.4-3.9-1.4-4.9-2.2
|
||||
c2.6-3,6.4-6.2,7.9-16.4c0.1-0.8,0-1.3,0-2c0-0.4,0.1-0.6,0.5-0.6c1.3-0.1,2.5-0.5,3.6-1.1c3.3-1.8,4.6-4.7,4.9-8.2
|
||||
C56.2,4.3,56.2,3.8,55.6,3.5z M27.1,35.1c-4.9-3.8-7.3-5.1-8.2-5.1c-0.9,0.1-0.8,1.1-0.5,1.8c0.2,0.7,0.5,1.1,0.9,1.7
|
||||
c0.3,0.4,0.4,1-0.3,1.4c-1.6,1-4.3-0.3-4.4-0.4c-3.2-1.9-5.9-4.4-7.7-7.7c-1.8-3.3-2.9-6.8-3-10.5c0-0.9,0.2-1.2,1.1-1.4
|
||||
c1.2-0.2,2.4-0.3,3.6-0.1c5,0.7,9.2,3,12.8,6.5c2,2,3.6,4.4,5.2,6.8c1.7,2.5,3.5,4.9,5.8,6.8c0.8,0.7,1.5,1.2,2.1,1.6
|
||||
C32.4,36.8,29.3,36.8,27.1,35.1z M29.5,20c0-0.4,0.3-0.7,0.7-0.7c0.1,0,0.2,0,0.2,0c0.1,0,0.2,0.1,0.3,0.2c0.1,0.1,0.2,0.3,0.2,0.5
|
||||
c0,0.4-0.3,0.7-0.7,0.7C29.8,20.8,29.5,20.4,29.5,20z M36.7,23.8c-0.5,0.2-0.9,0.4-1.4,0.4c-0.7,0-1.5-0.2-1.9-0.6
|
||||
c-0.6-0.5-1.1-0.8-1.3-1.8c-0.1-0.4,0-1,0-1.4c0.2-0.8,0-1.3-0.6-1.7c-0.4-0.4-1-0.5-1.6-0.5c-0.2,0-0.4-0.1-0.6-0.2
|
||||
c-0.3-0.1-0.5-0.4-0.3-0.8c0.1-0.1,0.4-0.4,0.4-0.5c0.8-0.5,1.8-0.3,2.7,0c0.8,0.3,1.4,1,2.3,1.8c0.9,1.1,1.1,1.3,1.6,2.1
|
||||
c0.4,0.6,0.8,1.3,1,2C37.5,23.2,37.3,23.6,36.7,23.8z"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 2.2 KiB |
1
web/public/images/ModelProvider/google-gemini.svg
Normal file
1
web/public/images/ModelProvider/google-gemini.svg
Normal file
@ -0,0 +1 @@
|
||||
<svg fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path d="M16 8.016A8.522 8.522 0 008.016 16h-.032A8.521 8.521 0 000 8.016v-.032A8.521 8.521 0 007.984 0h.032A8.522 8.522 0 0016 7.984v.032z" fill="url(#prefix__paint0_radial_980_20147)"/><defs><radialGradient id="prefix__paint0_radial_980_20147" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="matrix(16.1326 5.4553 -43.70045 129.2322 1.588 6.503)"><stop offset=".067" stop-color="#9168C0"/><stop offset=".343" stop-color="#5684D1"/><stop offset=".672" stop-color="#1BA1E3"/></radialGradient></defs></svg>
|
||||
|
After Width: | Height: | Size: 599 B |
@ -124,13 +124,13 @@ const ModalAddRemoteEngine = () => {
|
||||
<div className="space-y-2">
|
||||
<label htmlFor="chatCmpletionsUrl" className="font-semibold">
|
||||
{renderLabel(
|
||||
'API Endpoint URL',
|
||||
'Chat Completions URL',
|
||||
false,
|
||||
`The URL where Jan sends requests to access the AI provider's API.`
|
||||
)}
|
||||
</label>
|
||||
<Input
|
||||
placeholder="Enter API Endpoint URL"
|
||||
placeholder="Enter Chat Completions Endpoint URL"
|
||||
{...register('chatCmpletionsUrl')}
|
||||
/>
|
||||
{errors.chatCmpletionsUrl && (
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import { Engines, InferenceEngine } from '@janhq/core'
|
||||
|
||||
export const getLogoEngine = (engine: InferenceEngine) => {
|
||||
export const getLogoEngine = (engine: InferenceEngine | string) => {
|
||||
switch (engine) {
|
||||
case InferenceEngine.nitro:
|
||||
case InferenceEngine.cortex_llamacpp:
|
||||
@ -28,6 +28,11 @@ export const getLogoEngine = (engine: InferenceEngine) => {
|
||||
return 'images/ModelProvider/cohere.svg'
|
||||
case InferenceEngine.nvidia:
|
||||
return 'images/ModelProvider/nvidia.svg'
|
||||
// MARK: Deprecating InferenceEngine enum - as it's dynamically provided by the backend
|
||||
case 'google_gemini':
|
||||
return 'images/ModelProvider/google-gemini.svg'
|
||||
case 'deepseek':
|
||||
return 'images/ModelProvider/deepseek.svg'
|
||||
default:
|
||||
return undefined
|
||||
}
|
||||
@ -44,7 +49,7 @@ export const isLocalEngine = (engines?: Engines, engine?: string) => {
|
||||
return engines[engine as InferenceEngine]?.[0]?.type === 'local'
|
||||
}
|
||||
|
||||
export const getTitleByEngine = (engine: InferenceEngine) => {
|
||||
export const getTitleByEngine = (engine: InferenceEngine | string) => {
|
||||
switch (engine) {
|
||||
case InferenceEngine.nitro:
|
||||
case InferenceEngine.cortex_llamacpp:
|
||||
@ -59,6 +64,8 @@ export const getTitleByEngine = (engine: InferenceEngine) => {
|
||||
return 'OpenAI'
|
||||
case InferenceEngine.openrouter:
|
||||
return 'OpenRouter'
|
||||
case 'google_gemini':
|
||||
return 'Google Gemini'
|
||||
default:
|
||||
return engine.charAt(0).toUpperCase() + engine.slice(1)
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user