Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 03:32:23 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix: image token calc of OpenAI Compatible API (#3368)

Browse Source
This commit is contained in:
takatost 2024-04-11 20:29:48 +08:00 committed by GitHub
parent 693647a141
commit 9a1ea9ac03
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py
View File

@ -416,7 +416,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
if chunk.startswith(':'):
continue
decoded_chunk = chunk.strip().lstrip('data: ').lstrip()
chunk_json = None
try:
chunk_json = json.loads(decoded_chunk)
# stream ended
@ -620,7 +620,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
return message_dict
def _num_tokens_from_string(self, model: str, text: str,
def _num_tokens_from_string(self, model: str, text: Union[str, list[PromptMessageContent]],
tools: Optional[list[PromptMessageTool]] = None) -> int:
"""
Approximate num tokens for model with gpt2 tokenizer.
@ -630,7 +630,16 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
:param tools: tools for tool calling
:return: number of tokens
"""
num_tokens = self._get_num_tokens_by_gpt2(text)
if isinstance(text, str):
full_text = text
else:
full_text = ''
for message_content in text:
if message_content.type == PromptMessageContentType.TEXT:
message_content = cast(PromptMessageContent, message_content)
full_text += message_content.data
num_tokens = self._get_num_tokens_by_gpt2(full_text)
if tools:
num_tokens += self._num_tokens_for_tools(tools)