update spark v3.5, fix glm parallel problem
This commit is contained in:
binary-husky
parent
e359fff040
commit
dae180b9ea
@ -1,232 +0,0 @@
|
||||
from collections.abc import Callable, Iterable, Mapping
|
||||
from typing import Any
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import input_clipping, try_install_deps
|
||||
from multiprocessing import Process, Pipe
|
||||
import os
|
||||
import time
|
||||
|
||||
templete = """
|
||||
```python
|
||||
import ... # Put dependencies here, e.g. import numpy as np
|
||||
|
||||
class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
|
||||
|
||||
def run(self, path): # The name of the function must be `run`, it takes only a positional argument.
|
||||
# rewrite the function you have just written here
|
||||
...
|
||||
return generated_file_path
|
||||
```
|
||||
"""
|
||||
|
||||
def inspect_dependency(chatbot, history):
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return True
|
||||
|
||||
def get_code_block(reply):
|
||||
import re
|
||||
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
|
||||
matches = re.findall(pattern, reply) # find all code blocks in text
|
||||
if len(matches) == 1:
|
||||
return matches[0].strip('python') # code block
|
||||
for match in matches:
|
||||
if 'class TerminalFunction' in match:
|
||||
return match.strip('python') # code block
|
||||
raise RuntimeError("GPT is not generating proper code.")
|
||||
|
||||
def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
# 输入
|
||||
prompt_compose = [
|
||||
f'Your job:\n'
|
||||
f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
|
||||
f"2. You should write this function to perform following task: " + txt + "\n",
|
||||
f"3. Wrap the output python function with markdown codeblock."
|
||||
]
|
||||
i_say = "".join(prompt_compose)
|
||||
demo = []
|
||||
|
||||
# 第一步
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# 第二步
|
||||
prompt_compose = [
|
||||
"If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
|
||||
templete
|
||||
]
|
||||
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
code_to_return = gpt_say
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# # 第三步
|
||||
# i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
|
||||
# i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
# # # 第三步
|
||||
# i_say = "Show me how to use `pip` to install packages to run the code above. "
|
||||
# i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=i_say,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
installation_advance = ""
|
||||
|
||||
return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
|
||||
|
||||
def make_module(code):
|
||||
module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
|
||||
with open(f'{get_log_folder()}/{module_file}.py', 'w', encoding='utf8') as f:
|
||||
f.write(code)
|
||||
|
||||
def get_class_name(class_string):
|
||||
import re
|
||||
# Use regex to extract the class name
|
||||
class_name = re.search(r'class (\w+)\(', class_string).group(1)
|
||||
return class_name
|
||||
|
||||
class_name = get_class_name(code)
|
||||
return f"{get_log_folder().replace('/', '.')}.{module_file}->{class_name}"
|
||||
|
||||
def init_module_instance(module):
|
||||
import importlib
|
||||
module_, class_ = module.split('->')
|
||||
init_f = getattr(importlib.import_module(module_), class_)
|
||||
return init_f()
|
||||
|
||||
def for_immediate_show_off_when_possible(file_type, fp, chatbot):
|
||||
if file_type in ['png', 'jpg']:
|
||||
image_path = os.path.abspath(fp)
|
||||
chatbot.append(['这是一张图片, 展示如下:',
|
||||
f'本地文件地址: <br/>`{image_path}`<br/>'+
|
||||
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
|
||||
])
|
||||
return chatbot
|
||||
|
||||
def subprocess_worker(instance, file_path, return_dict):
|
||||
return_dict['result'] = instance.run(file_path)
|
||||
|
||||
def have_any_recent_upload_files(chatbot):
|
||||
_5min = 5 * 60
|
||||
if not chatbot: return False # chatbot is None
|
||||
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
|
||||
if not most_recent_uploaded: return False # most_recent_uploaded is None
|
||||
if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
|
||||
else: return False # most_recent_uploaded is too old
|
||||
|
||||
def get_recent_file_prompt_support(chatbot):
|
||||
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
|
||||
path = most_recent_uploaded['path']
|
||||
return path
|
||||
|
||||
@CatchException
|
||||
def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行
|
||||
plugin_kwargs 插件模型的参数，暂时没有用武之地
|
||||
chatbot 聊天显示框的句柄，用于显示给用户
|
||||
history 聊天历史，前情提要
|
||||
system_prompt 给gpt的静默提醒
|
||||
user_request 当前用户的请求信息（IP地址等）
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
# 清空历史，以免输入溢出
|
||||
history = []; clear_file_downloadzone(chatbot)
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 插件初始化中 ..."
|
||||
])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
if have_any_recent_upload_files(chatbot):
|
||||
file_path = get_recent_file_prompt_support(chatbot)
|
||||
else:
|
||||
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 读取文件
|
||||
if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
|
||||
recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
|
||||
file_path = recently_uploaded_files[-1]
|
||||
file_type = file_path.split('.')[-1]
|
||||
|
||||
# 粗心检查
|
||||
if is_the_upload_folder(txt):
|
||||
chatbot.append([
|
||||
"...",
|
||||
f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
|
||||
])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始干正事
|
||||
for j in range(5): # 最多重试5次
|
||||
try:
|
||||
code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
|
||||
yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
|
||||
code = get_code_block(code)
|
||||
res = make_module(code)
|
||||
instance = init_module_instance(res)
|
||||
break
|
||||
except Exception as e:
|
||||
chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 代码生成结束, 开始执行
|
||||
try:
|
||||
import multiprocessing
|
||||
manager = multiprocessing.Manager()
|
||||
return_dict = manager.dict()
|
||||
|
||||
p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
|
||||
# only has 10 seconds to run
|
||||
p.start(); p.join(timeout=10)
|
||||
if p.is_alive(): p.terminate(); p.join()
|
||||
p.close()
|
||||
res = return_dict['result']
|
||||
# res = instance.run(file_path)
|
||||
except Exception as e:
|
||||
chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
# chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 顺利完成，收尾
|
||||
res = str(res)
|
||||
if os.path.exists(res):
|
||||
chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
|
||||
new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
else:
|
||||
chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
"""
|
||||
测试：
|
||||
裁剪图像，保留下半部分
|
||||
交换图像的蓝色通道和红色通道
|
||||
将图像转为灰度图像
|
||||
将csv文件转excel表格
|
||||
"""
|
||||
@ -12,7 +12,7 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
mode = 'input-and-history'
|
||||
# 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
|
||||
input_token_num = get_token_num(inputs)
|
||||
if input_token_num < max_token_limit//2:
|
||||
if input_token_num < max_token_limit//2:
|
||||
mode = 'only-history'
|
||||
max_token_limit = max_token_limit - input_token_num
|
||||
|
||||
@ -21,7 +21,7 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
n_token = get_token_num('\n'.join(everything))
|
||||
everything_token = [get_token_num(e) for e in everything]
|
||||
delta = max(everything_token) // 16 # 截断时的颗粒度
|
||||
|
||||
|
||||
while n_token > max_token_limit:
|
||||
where = np.argmax(everything_token)
|
||||
encoded = enc.encode(everything[where], disallowed_special=())
|
||||
@ -38,9 +38,9 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
return inputs, history
|
||||
|
||||
def request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs, inputs_show_user, llm_kwargs,
|
||||
inputs, inputs_show_user, llm_kwargs,
|
||||
chatbot, history, sys_prompt, refresh_interval=0.2,
|
||||
handle_token_exceed=True,
|
||||
handle_token_exceed=True,
|
||||
retry_times_at_unknown_error=2,
|
||||
):
|
||||
"""
|
||||
@ -77,7 +77,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
|
||||
exceeded_cnt = 0
|
||||
while True:
|
||||
# watchdog error
|
||||
if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
|
||||
if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
|
||||
raise RuntimeError("检测到程序终止。")
|
||||
try:
|
||||
# 【第一种情况】：顺利完成
|
||||
@ -140,12 +140,12 @@ def can_multi_process(llm):
|
||||
if llm.startswith('api2d-'): return True
|
||||
if llm.startswith('azure-'): return True
|
||||
if llm.startswith('spark'): return True
|
||||
if llm.startswith('zhipuai'): return True
|
||||
if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
|
||||
return False
|
||||
|
||||
def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
inputs_array, inputs_show_user_array, llm_kwargs,
|
||||
chatbot, history_array, sys_prompt_array,
|
||||
inputs_array, inputs_show_user_array, llm_kwargs,
|
||||
chatbot, history_array, sys_prompt_array,
|
||||
refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
|
||||
handle_token_exceed=True, show_user_at_complete=False,
|
||||
retry_times_at_unknown_error=2,
|
||||
@ -189,7 +189,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
# 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
|
||||
if not can_multi_process(llm_kwargs['llm_model']):
|
||||
max_workers = 1
|
||||
|
||||
|
||||
executor = ThreadPoolExecutor(max_workers=max_workers)
|
||||
n_frag = len(inputs_array)
|
||||
# 用户反馈
|
||||
@ -214,7 +214,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
try:
|
||||
# 【第一种情况】：顺利完成
|
||||
gpt_say = predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=history,
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=history,
|
||||
sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
|
||||
)
|
||||
mutable[index][2] = "已成功"
|
||||
@ -246,7 +246,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
print(tb_str)
|
||||
gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
|
||||
if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
|
||||
if retry_op > 0:
|
||||
if retry_op > 0:
|
||||
retry_op -= 1
|
||||
wait = random.randint(5, 20)
|
||||
if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
|
||||
@ -287,8 +287,8 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
|
||||
observe_win.append(print_something_really_funny)
|
||||
# 在前端打印些好玩的东西
|
||||
stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
|
||||
if not done else f'`{mutable[thread_index][2]}`\n\n'
|
||||
stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
|
||||
if not done else f'`{mutable[thread_index][2]}`\n\n'
|
||||
for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
|
||||
# 在前端打印些好玩的东西
|
||||
chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
|
||||
@ -302,7 +302,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
for inputs_show_user, f in zip(inputs_show_user_array, futures):
|
||||
gpt_res = f.result()
|
||||
gpt_response_collection.extend([inputs_show_user, gpt_res])
|
||||
|
||||
|
||||
# 是否在结束时，在界面上显示结果
|
||||
if show_user_at_complete:
|
||||
for inputs_show_user, f in zip(inputs_show_user_array, futures):
|
||||
@ -352,7 +352,7 @@ def read_and_clean_pdf_text(fp):
|
||||
if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
|
||||
fsize_statiscs[wtf['size']] += len(wtf['text'])
|
||||
return max(fsize_statiscs, key=fsize_statiscs.get)
|
||||
|
||||
|
||||
def ffsize_same(a,b):
|
||||
"""
|
||||
提取字体大小是否近似相等
|
||||
@ -388,7 +388,7 @@ def read_and_clean_pdf_text(fp):
|
||||
if index == 0:
|
||||
page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
|
||||
'- ', '') for t in text_areas['blocks'] if 'lines' in t]
|
||||
|
||||
|
||||
############################## <第 2 步，获取正文主字体> ##################################
|
||||
try:
|
||||
fsize_statiscs = {}
|
||||
@ -404,7 +404,7 @@ def read_and_clean_pdf_text(fp):
|
||||
mega_sec = []
|
||||
sec = []
|
||||
for index, line in enumerate(meta_line):
|
||||
if index == 0:
|
||||
if index == 0:
|
||||
sec.append(line[fc])
|
||||
continue
|
||||
if REMOVE_FOOT_NOTE:
|
||||
@ -501,12 +501,12 @@ def get_files_from_everything(txt, type): # type='.md'
|
||||
"""
|
||||
这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
|
||||
下面是对每个参数和返回值的说明：
|
||||
参数
|
||||
- txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
|
||||
参数
|
||||
- txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
|
||||
- type: 字符串，表示要搜索的文件类型。默认是.md。
|
||||
返回值
|
||||
- success: 布尔值，表示函数是否成功执行。
|
||||
- file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
|
||||
返回值
|
||||
- success: 布尔值，表示函数是否成功执行。
|
||||
- file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
|
||||
- project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
|
||||
该函数详细注释已添加，请确认是否满足您的需要。
|
||||
"""
|
||||
@ -570,7 +570,7 @@ class nougat_interface():
|
||||
def NOUGAT_parse_pdf(self, fp, chatbot, history):
|
||||
from toolbox import update_ui_lastest_msg
|
||||
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
self.threadLock.acquire()
|
||||
import glob, threading, os
|
||||
@ -578,7 +578,7 @@ class nougat_interface():
|
||||
dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
|
||||
os.makedirs(dst)
|
||||
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd(), timeout=3600)
|
||||
res = glob.glob(os.path.join(dst,'*.mmd'))
|
||||
|
||||
@ -560,7 +560,7 @@ if "sparkv2" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
if "sparkv3" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
try:
|
||||
from .bridge_spark import predict_no_ui_long_connection as spark_noui
|
||||
from .bridge_spark import predict as spark_ui
|
||||
@ -572,6 +572,14 @@ if "sparkv3" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"sparkv3.5": {
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
})
|
||||
except:
|
||||
|
||||
@ -65,6 +65,7 @@ class SparkRequestInstance():
|
||||
self.gpt_url = "ws://spark-api.xf-yun.com/v1.1/chat"
|
||||
self.gpt_url_v2 = "ws://spark-api.xf-yun.com/v2.1/chat"
|
||||
self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
|
||||
self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
|
||||
self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
|
||||
|
||||
self.time_to_yield_event = threading.Event()
|
||||
@ -91,6 +92,8 @@ class SparkRequestInstance():
|
||||
gpt_url = self.gpt_url_v2
|
||||
elif llm_kwargs['llm_model'] == 'sparkv3':
|
||||
gpt_url = self.gpt_url_v3
|
||||
elif llm_kwargs['llm_model'] == 'sparkv3.5':
|
||||
gpt_url = self.gpt_url_v35
|
||||
else:
|
||||
gpt_url = self.gpt_url
|
||||
file_manifest = []
|
||||
@ -190,6 +193,7 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
|
||||
"spark": "general",
|
||||
"sparkv2": "generalv2",
|
||||
"sparkv3": "generalv3",
|
||||
"sparkv3.5": "generalv3.5",
|
||||
}
|
||||
domains_select = domains[llm_kwargs['llm_model']]
|
||||
if file_manifest: domains_select = 'image'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user