Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix JSONDecodeError for Ollama and hide LiteLLM vision support warning #1524

Open
wants to merge 2 commits into
base: development
Choose a base branch
from
Open

Fix JSONDecodeError for Ollama and hide LiteLLM vision support warning #1524

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6b4a298
Fixed json_encode error
CyanideByte Nov 5, 2024
4a1fa7c
Hide litellm model not mapped error
CyanideByte Nov 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions interpreter/core/llm/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,15 +26,13 @@
# Create or get the logger
logger = logging.getLogger("LiteLLM")


class SuppressDebugFilter(logging.Filter):
def filter(self, record):
# Suppress only the specific message containing the keywords
if "cost map" in record.getMessage():
if "cost map" in record.getMessage() or "vision support" in record.getMessage():
return False # Suppress this log message
return True # Allow all other messages


class Llm:
"""
A stateless LMC-style LLM with some helpful properties.
Expand Down
2 changes: 2 additions & 0 deletions interpreter/terminal_interface/local_setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -303,6 +303,7 @@ def download_model(models_dir, models, interpreter):

# Set the model to the selected model
interpreter.llm.model = f"ollama/{model}"
interpreter.llm.supports_functions = False

# Send a ping, which will actually load the model

Expand Down Expand Up @@ -373,6 +374,7 @@ def download_model(models_dir, models, interpreter):

interpreter.llm.model = jan_model_name
interpreter.llm.api_key = "dummy"
interpreter.llm.supports_functions = False
interpreter.display_message(f"\nUsing Jan model: `{jan_model_name}` \n")
# time.sleep(1)

Expand Down
Loading