xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-05 05:10:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: improve Ollama and Hugging Face model configuration docs

Browse Source
This commit is contained in:
mrT23
2025-01-02 11:16:21 +02:00
parent f6b470bf5e
commit 5971a06d73
3 changed files with 7 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docs/docs/usage-guide/changing_a_model.md
View File

@ -30,50 +30,30 @@ model="" # the OpenAI model you've deployed on Azure (e.g. gpt-4o)
fallback_models=["..."] fallback_models=["..."]
``` ```
### Hugging Face ### Ollama
**Local** **Local**
You can run Hugging Face models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama) You can run Hugging Face models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
E.g. to use a new Hugging Face model locally via Ollama, set: E.g. to use a new Hugging Face model locally via Ollama, set:
``` ```
[__init__.py]
MAX_TOKENS = {
"model-name-on-ollama": <max_tokens>
}
e.g.
MAX_TOKENS={
...,
"ollama/llama2": 4096
}
[config] # in configuration.toml [config] # in configuration.toml
model = "ollama/llama2" model = "ollama/llama2"
fallback_models=["ollama/llama2"] fallback_models=["ollama/llama2"]
custom_model_max_tokens=... # set the maximal input tokens for the model
[ollama] # in .secrets.toml [ollama] # in .secrets.toml
api_base = ... # the base url for your Hugging Face inference endpoint api_base = "http://localhost:11434" # or whatever port you're running Ollama on
# e.g. if running Ollama locally, you may use:
api_base = "http://localhost:11434/"
``` ```
### Inference Endpoints ### Hugging Face Inference Endpoints
To use a new model with Hugging Face Inference Endpoints, for example, set: To use a new model with Hugging Face Inference Endpoints, for example, set:
``` ```
[__init__.py]
MAX_TOKENS = {
"model-name-on-huggingface": <max_tokens>
}
e.g.
MAX_TOKENS={
...,
"meta-llama/Llama-2-7b-chat-hf": 4096
}
[config] # in configuration.toml [config] # in configuration.toml
model = "huggingface/meta-llama/Llama-2-7b-chat-hf" model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"] fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"]
custom_model_max_tokens=... # set the maximal input tokens for the model
[huggingface] # in .secrets.toml [huggingface] # in .secrets.toml
key = ... # your Hugging Face api key key = ... # your Hugging Face api key

2
pr_agent/config_loader.py
View File

@ -12,7 +12,6 @@ global_settings = Dynaconf(
envvar_prefix=False, envvar_prefix=False,
merge_enabled=True, merge_enabled=True,
settings_files=[join(current_dir, f) for f in [ settings_files=[join(current_dir, f) for f in [
"settings/.secrets.toml",
"settings/configuration.toml", "settings/configuration.toml",
"settings/ignore.toml", "settings/ignore.toml",
"settings/language_extensions.toml", "settings/language_extensions.toml",
@ -29,6 +28,7 @@ global_settings = Dynaconf(
"settings/pr_add_docs.toml", "settings/pr_add_docs.toml",
"settings/custom_labels.toml", "settings/custom_labels.toml",
"settings/pr_help_prompts.toml", "settings/pr_help_prompts.toml",
"settings/.secrets.toml",
"settings_prod/.secrets.toml", "settings_prod/.secrets.toml",
]] ]]
) )

2
pr_agent/settings/configuration.toml
View File

@ -2,6 +2,7 @@
# models # models
model="gpt-4o-2024-11-20" model="gpt-4o-2024-11-20"
fallback_models=["gpt-4o-2024-08-06"] fallback_models=["gpt-4o-2024-08-06"]
custom_model_max_tokens=-1 # for models not in the default list
#model_weak="gpt-4o-mini-2024-07-18" # optional, a weaker model to use for some easier tasks #model_weak="gpt-4o-mini-2024-07-18" # optional, a weaker model to use for some easier tasks
# CLI # CLI
git_provider="github" git_provider="github"
@ -21,7 +22,6 @@ skip_keys = []
max_description_tokens = 500 max_description_tokens = 500
max_commits_tokens = 500 max_commits_tokens = 500
max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities. max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
custom_model_max_tokens=-1 # for models not in the default list
# patch extension logic # patch extension logic
patch_extension_skip_types =[".md",".txt"] patch_extension_skip_types =[".md",".txt"]
allow_dynamic_context=true allow_dynamic_context=true