diff --git a/docs/docs/usage-guide/changing_a_model.md b/docs/docs/usage-guide/changing_a_model.md index ec7bef31f..57e0787eb 100644 --- a/docs/docs/usage-guide/changing_a_model.md +++ b/docs/docs/usage-guide/changing_a_model.md @@ -5,7 +5,7 @@ To use a different model than the default (GPT-4), you need to edit in the [conf ``` [config] model = "..." -model_week = "..." +model_weak = "..." fallback_models = ["..."] ``` @@ -28,7 +28,7 @@ and set in your configuration file: ``` [config] model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo) -model_week="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo) +model_weak="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo) fallback_models=["..."] # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo) ``` @@ -52,7 +52,7 @@ MAX_TOKENS={ [config] # in configuration.toml model = "ollama/llama2" -model_week = "ollama/llama2" +model_weak = "ollama/llama2" fallback_models=["ollama/llama2"] [ollama] # in .secrets.toml @@ -76,7 +76,7 @@ MAX_TOKENS={ } [config] # in configuration.toml model = "huggingface/meta-llama/Llama-2-7b-chat-hf" -model_week = "huggingface/meta-llama/Llama-2-7b-chat-hf" +model_weak = "huggingface/meta-llama/Llama-2-7b-chat-hf" fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"] [huggingface] # in .secrets.toml @@ -91,7 +91,7 @@ To use Llama2 model with Replicate, for example, set: ``` [config] # in configuration.toml model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1" -model_week = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1" +model_weak = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1" fallback_models=["replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"] [replicate] # in .secrets.toml key = ... @@ -107,7 +107,7 @@ To use Llama3 model with Groq, for example, set: ``` [config] # in configuration.toml model = "llama3-70b-8192" -model_week = "llama3-70b-8192" +model_weak = "llama3-70b-8192" fallback_models = ["groq/llama3-70b-8192"] [groq] # in .secrets.toml key = ... # your Groq api key @@ -121,7 +121,7 @@ To use Google's Vertex AI platform and its associated models (chat-bison/codecha ``` [config] # in configuration.toml model = "vertex_ai/codechat-bison" -model_week = "vertex_ai/codechat-bison" +model_weak = "vertex_ai/codechat-bison" fallback_models="vertex_ai/codechat-bison" [vertexai] # in .secrets.toml @@ -140,7 +140,7 @@ To use [Google AI Studio](https://aistudio.google.com/) models, set the relevant ```toml [config] # in configuration.toml model="google_ai_studio/gemini-1.5-flash" -model_week="google_ai_studio/gemini-1.5-flash" +model_weak="google_ai_studio/gemini-1.5-flash" fallback_models=["google_ai_studio/gemini-1.5-flash"] [google_ai_studio] # in .secrets.toml @@ -156,7 +156,7 @@ To use Anthropic models, set the relevant models in the configuration section of ``` [config] model="anthropic/claude-3-opus-20240229" -model_week="anthropic/claude-3-opus-20240229" +model_weak="anthropic/claude-3-opus-20240229" fallback_models=["anthropic/claude-3-opus-20240229"] ``` @@ -173,7 +173,7 @@ To use Amazon Bedrock and its foundational models, add the below configuration: ``` [config] # in configuration.toml model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0" -model_week="bedrock/anthropic.claude-3-sonnet-20240229-v1:0" +model_weak="bedrock/anthropic.claude-3-sonnet-20240229-v1:0" fallback_models=["bedrock/anthropic.claude-v2:1"] ``` @@ -195,7 +195,7 @@ If the relevant model doesn't appear [here](https://github.com/Codium-ai/pr-agen ``` [config] model="custom_model_name" -model_week="custom_model_name" +model_weak="custom_model_name" fallback_models=["custom_model_name"] ``` (2) Set the maximal tokens for the model: diff --git a/pr_agent/algo/pr_processing.py b/pr_agent/algo/pr_processing.py index 447a1322e..d3df09f81 100644 --- a/pr_agent/algo/pr_processing.py +++ b/pr_agent/algo/pr_processing.py @@ -355,7 +355,7 @@ async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelT def _get_all_models(model_type: ModelType = ModelType.WEAK) -> List[str]: if model_type == ModelType.WEAK: - model = get_settings().config.model_week + model = get_settings().config.model_weak else: model = get_settings().config.model fallback_models = get_settings().config.fallback_models diff --git a/pr_agent/git_providers/utils.py b/pr_agent/git_providers/utils.py index 9f4974d40..6038e8610 100644 --- a/pr_agent/git_providers/utils.py +++ b/pr_agent/git_providers/utils.py @@ -99,5 +99,5 @@ def set_claude_model(): """ model_claude = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0" get_settings().set('config.model', model_claude) - get_settings().set('config.model_week', model_claude) + get_settings().set('config.model_weak', model_claude) get_settings().set('config.fallback_models', [model_claude]) diff --git a/pr_agent/settings/configuration.toml b/pr_agent/settings/configuration.toml index da5dfbdfe..e4a0ac8ab 100644 --- a/pr_agent/settings/configuration.toml +++ b/pr_agent/settings/configuration.toml @@ -1,6 +1,6 @@ [config] # models -model_week="gpt-4o-mini-2024-07-18" +model_weak="gpt-4o-mini-2024-07-18" model="gpt-4o-2024-11-20" fallback_models=["gpt-4o-2024-08-06"] # CLI