estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(large_language_model): Adds plugin-based token counting configuration option (#17706)

Browse Source 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
This commit is contained in:
-LAN-
2025-04-09 21:52:58 +09:00
committed by GitHub
parent 8b3be4224d
commit d3157b46ee
10 changed files with 32 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
api/core/app/apps/agent_chat/app_runner.py
View File

@@ -53,20 +53,6 @@ class AgentChatAppRunner(AppRunner):
query = application_generate_entity.query
files = application_generate_entity.files
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=dict(inputs),
files=list(files),
query=query,
)
memory = None
if application_generate_entity.conversation_id:
# get memory of conversation (read-only)

14
api/core/app/apps/chat/app_runner.py
View File

@@ -61,20 +61,6 @@ class ChatAppRunner(AppRunner):
)
image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=inputs,
files=files,
query=query,
)
memory = None
if application_generate_entity.conversation_id:
# get memory of conversation (read-only)

14
api/core/app/apps/completion/app_runner.py
View File

@@ -54,20 +54,6 @@ class CompletionAppRunner(AppRunner):
)
image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=inputs,
files=files,
query=query,
)
# organize all inputs and template to prompt messages
# Include: prompt template, inputs, query(optional), files(optional)
prompt_messages, stop = self.organize_prompt_messages(