AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-10 16:58:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add gpt-3.5-turbo-16k support and update openai gpt-3.5-turbo & Embedding Ada v2 unit price (#358)

Browse Source
This commit is contained in:
John Wang 2023-06-14 12:17:43 +08:00 committed by GitHub
parent ab115b5f87
commit 184afa69ff
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
api/core/constant/llm_constant.py
View File

@ -4,6 +4,7 @@ models = {
'gpt-4': 'openai', # 8,192 tokens
'gpt-4-32k': 'openai', # 32,768 tokens
'gpt-3.5-turbo': 'openai', # 4,096 tokens
'gpt-3.5-turbo-16k': 'openai', # 16384 tokens
'text-davinci-003': 'openai', # 4,097 tokens
'text-davinci-002': 'openai', # 4,097 tokens
'text-curie-001': 'openai', # 2,049 tokens
@ -16,6 +17,7 @@ max_context_token_length = {
'gpt-4': 8192,
'gpt-4-32k': 32768,
'gpt-3.5-turbo': 4096,
'gpt-3.5-turbo-16k': 16384,
'text-davinci-003': 4097,
'text-davinci-002': 4097,
'text-curie-001': 2049,
@ -29,11 +31,13 @@ models_by_mode = {
'gpt-4', # 8,192 tokens
'gpt-4-32k', # 32,768 tokens
'gpt-3.5-turbo', # 4,096 tokens
'gpt-3.5-turbo-16k', # 16,384 tokens
],
'completion': [
'gpt-4', # 8,192 tokens
'gpt-4-32k', # 32,768 tokens
'gpt-3.5-turbo', # 4,096 tokens
'gpt-3.5-turbo-16k', # 16,384 tokens
'text-davinci-003', # 4,097 tokens
'text-davinci-002' # 4,097 tokens
'text-curie-001', # 2,049 tokens
@ -57,9 +61,13 @@ model_prices = {
'completion': Decimal('0.12')
},
'gpt-3.5-turbo': {
'prompt': Decimal('0.002'),
'prompt': Decimal('0.0015'),
'completion': Decimal('0.002')
},
'gpt-3.5-turbo-16k': {
'prompt': Decimal('0.003'),
'completion': Decimal('0.004')
},
'text-davinci-003': {
'prompt': Decimal('0.02'),
'completion': Decimal('0.02')
@ -77,7 +85,7 @@ model_prices = {
'completion': Decimal('0.0004')
},
'text-embedding-ada-002': {
'usage': Decimal('0.0004'),
'usage': Decimal('0.0001'),
}
}

3
api/core/llm/provider/azure_provider.py
View File

@ -95,7 +95,8 @@ class AzureProvider(BaseProvider):
if not models:
raise ValidateFailedError("Please add deployments for 'text-davinci-003', "
"'gpt-3.5-turbo', 'text-embedding-ada-002'.")
"'gpt-3.5-turbo', 'text-embedding-ada-002' (required) "
"and 'gpt-4', 'gpt-35-turbo-16k' (optional).")
fixed_model_ids = [
'text-davinci-003',

2
web/app/components/app/configuration/config-model/index.tsx
View File

@ -26,8 +26,10 @@ export type IConifgModelProps = {
const options = [
{ id: 'gpt-3.5-turbo', name: 'gpt-3.5-turbo', type: AppType.chat },
{ id: 'gpt-3.5-turbo-16k', name: 'gpt-3.5-turbo-16k', type: AppType.chat },
{ id: 'gpt-4', name: 'gpt-4', type: AppType.chat }, // 8k version
{ id: 'gpt-3.5-turbo', name: 'gpt-3.5-turbo', type: AppType.completion },
{ id: 'gpt-3.5-turbo-16k', name: 'gpt-3.5-turbo-16k', type: AppType.completion },
{ id: 'text-davinci-003', name: 'text-davinci-003', type: AppType.completion },
{ id: 'gpt-4', name: 'gpt-4', type: AppType.completion }, // 8k version
]