vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix llm cost for gpt4.1 (#2172)

Browse Source
This commit is contained in:
Shuchang Zheng
2025-04-16 15:32:51 -07:00
committed by GitHub
parent e28f769010
commit 3154a9ce10
3 changed files with 348 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

405
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

4
pyproject.toml
View File

@@ -9,14 +9,14 @@ packages = [{ include = "skyvern" }, { include = "alembic" }]
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.11,<3.12" python = "^3.11,<3.12"
python-dotenv = "^1.0.0" python-dotenv = "^1.0.0"
openai = "<1.68" openai = ">=1.68.2"
sqlalchemy = {extras = ["mypy"], version = "^2.0.29"} sqlalchemy = {extras = ["mypy"], version = "^2.0.29"}
aiohttp = "^3.8.5" aiohttp = "^3.8.5"
python-multipart = "^0.0.6" python-multipart = "^0.0.6"
toml = "^0.10.2" toml = "^0.10.2"
jinja2 = "^3.1.2" jinja2 = "^3.1.2"
uvicorn = {extras = ["standard"], version = "^0.24.0.post1"} uvicorn = {extras = ["standard"], version = "^0.24.0.post1"}
litellm = "^1.63.12" litellm = "1.66.1"
playwright = "1.46.0" playwright = "1.46.0"
pillow = "^10.1.0" pillow = "^10.1.0"
starlette-context = "^0.3.6" starlette-context = "^0.3.6"

4
skyvern/forge/sdk/api/llm/api_handler_factory.py
View File

@@ -160,7 +160,7 @@ class LLMAPIHandlerFactory:
try: try:
llm_cost = litellm.completion_cost(completion_response=response) llm_cost = litellm.completion_cost(completion_response=response)
except Exception as e: except Exception as e:
LOG.exception("Failed to calculate LLM cost", error=str(e)) LOG.debug("Failed to calculate LLM cost", error=str(e), exc_info=True)
llm_cost = 0 llm_cost = 0
prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0) prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0)
completion_tokens = response.get("usage", {}).get("completion_tokens", 0) completion_tokens = response.get("usage", {}).get("completion_tokens", 0)
@@ -350,7 +350,7 @@ class LLMAPIHandlerFactory:
try: try:
llm_cost = litellm.completion_cost(completion_response=response) llm_cost = litellm.completion_cost(completion_response=response)
except Exception as e: except Exception as e:
LOG.exception("Failed to calculate LLM cost", error=str(e)) LOG.debug("Failed to calculate LLM cost", error=str(e), exc_info=True)
llm_cost = 0 llm_cost = 0
prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0) prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0)
completion_tokens = response.get("usage", {}).get("completion_tokens", 0) completion_tokens = response.get("usage", {}).get("completion_tokens", 0)