ivanwu/jarvis-models
1
0
Fork 0
mirror of https://github.com/BoardWare-Genius/jarvis-models.git synced 2025-12-14 00:53:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: remove sample data and support cicd

Browse Source
This commit is contained in:
Ivan087
2025-09-18 10:55:27 +08:00
parent ced10e4447
commit 913fc07bc8
37 changed files with 105 additions and 50575 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
src/blackbox/vlms.py
View File

@ -22,7 +22,7 @@ from time import time
import io
from PIL import Image
from lmdeploy.serve.openai.api_client import APIClient
# from lmdeploy.serve.openai.api_client import APIClient
from openai import OpenAI
@ -184,40 +184,34 @@ class VLMS(Blackbox):
total_token_usage = 0 # which can be used to count the cost of a query
model_url = self._get_model_url(config['vlm_model_name'])
if config['lmdeploy_infer']:
api_client = APIClient(model_url)
model_name = api_client.available_models[0]
for i,item in enumerate(api_client.chat_completions_v1(model=model_name,
messages=messages,stream = True,
**settings,
# session_id=,
)):
# Stream output
yield item["choices"][0]["delta"]['content']
responses += item["choices"][0]["delta"]['content']
# if config['lmdeploy_infer']:
# # api_client = APIClient(model_url)
# # model_name = api_client.available_models[0]
# for i,item in enumerate(api_client.chat_completions_v1(model=model_name,
# messages=messages,stream = True,
# **settings,
# # session_id=,
# )):
# # Stream output
# yield item["choices"][0]["delta"]['content']
# responses += item["choices"][0]["delta"]['content']
# print(item["choices"][0]["message"]['content'])
# responses += item["choices"][0]["message"]['content']
# total_token_usage += item['usage']['total_tokens'] # 'usage': {'prompt_tokens': *, 'total_tokens': *, 'completion_tokens': *}
else:
api_key = "EMPTY_API_KEY"
api_client = OpenAI(api_key=api_key, base_url=model_url+'/v1')
model_name = api_client.models.list().data[0].id
for item in api_client.chat.completions.create(
model=model_name,
messages=messages,
temperature=0.8,
top_p=0.8,
stream=True):
yield(item.choices[0].delta.content)
responses += item.choices[0].delta.content
# response = api_client.chat.completions.create(
# model=model_name,
# messages=messages,
# temperature=0.8,
# top_p=0.8)
# print(response.choices[0].message.content)
# return response.choices[0].message.content
# # print(item["choices"][0]["message"]['content'])
# # responses += item["choices"][0]["message"]['content']
# # total_token_usage += item['usage']['total_tokens'] # 'usage': {'prompt_tokens': *, 'total_tokens': *, 'completion_tokens': *}
# else:
api_key = "EMPTY_API_KEY"
api_client = OpenAI(api_key=api_key, base_url=model_url+'/v1')
model_name = api_client.models.list().data[0].id
for item in api_client.chat.completions.create(
model=model_name,
messages=messages,
**settings,
stream=True):
yield(item.choices[0].delta.content)
responses += item.choices[0].delta.content
# print(response.choices[0].message.content)
# return response.choices[0].message.content
user_context = messages + [{'role': 'assistant', 'content': responses}]