Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 11:42:29 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix: Ollama modelfeature set vision, and an exception occurred at the… (#8783)

Browse Source
This commit is contained in:
cx 2024-09-26 16:34:40 +08:00 committed by GitHub
parent 62406991df
commit 128a66f7fe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
api/core/model_runtime/model_providers/ollama/llm/llm.py
View File

@ -364,14 +364,21 @@ class OllamaLargeLanguageModel(LargeLanguageModel):
if chunk_json["done"]:
# calculate num tokens
if "prompt_eval_count" in chunk_json and "eval_count" in chunk_json:
# transform usage
if "prompt_eval_count" in chunk_json:
prompt_tokens = chunk_json["prompt_eval_count"]
completion_tokens = chunk_json["eval_count"]
else:
# calculate num tokens
prompt_tokens = self._get_num_tokens_by_gpt2(prompt_messages[0].content)
completion_tokens = self._get_num_tokens_by_gpt2(full_text)
prompt_message_content = prompt_messages[0].content
if isinstance(prompt_message_content, str):
prompt_tokens = self._get_num_tokens_by_gpt2(prompt_message_content)
else:
content_text = ""
for message_content in prompt_message_content:
if message_content.type == PromptMessageContentType.TEXT:
message_content = cast(TextPromptMessageContent, message_content)
content_text += message_content.data
prompt_tokens = self._get_num_tokens_by_gpt2(content_text)
completion_tokens = chunk_json.get("eval_count", self._get_num_tokens_by_gpt2(full_text))
# transform usage
usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)