xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 12:20:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #877 from randy-tsukemen/support-groq-llama3

Browse Source 
Add Groq Llama3 support
This commit is contained in:
Tal
2024-04-22 11:41:12 +03:00
committed by GitHub
parent 19f239ae3d d457fa2b9f
commit fae6cab2a7
4 changed files with 20 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/docs/usage-guide/additional_configurations.md
View File

@ -125,6 +125,19 @@ key = ...
Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models. Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models.
### Groq
To use Llama3 model with Groq, for example, set:
```
[config] # in configuration.toml
model = "llama3-70b-8192"
model_turbo = "llama3-70b-8192"
fallback_models = ["groq/llama3-70b-8192"]
[groq] # in .secrets.toml
key = ... # your Groq api key
```
(you can obtain a Groq key from [here](https://console.groq.com/keys))
### Vertex AI ### Vertex AI
To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set: To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:

2
pr_agent/algo/__init__.py
View File

@ -31,4 +31,6 @@ MAX_TOKENS = {
'bedrock/anthropic.claude-v2:1': 100000, 'bedrock/anthropic.claude-v2:1': 100000,
'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000, 'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000,
'bedrock/anthropic.claude-3-haiku-20240307-v1:0': 100000, 'bedrock/anthropic.claude-3-haiku-20240307-v1:0': 100000,
'groq/llama3-8b-8192': 8192,
'groq/llama3-70b-8192': 8192,
} }

2
pr_agent/algo/ai_handlers/litellm_ai_handler.py
View File

@ -52,6 +52,8 @@ class LiteLLMAIHandler(BaseAiHandler):
litellm.anthropic_key = get_settings().anthropic.key litellm.anthropic_key = get_settings().anthropic.key
if get_settings().get("COHERE.KEY", None): if get_settings().get("COHERE.KEY", None):
litellm.cohere_key = get_settings().cohere.key litellm.cohere_key = get_settings().cohere.key
if get_settings().get("GROQ.KEY", None):
litellm.api_key = get_settings().groq.key
if get_settings().get("REPLICATE.KEY", None): if get_settings().get("REPLICATE.KEY", None):
litellm.replicate_key = get_settings().replicate.key litellm.replicate_key = get_settings().replicate.key
if get_settings().get("HUGGINGFACE.KEY", None): if get_settings().get("HUGGINGFACE.KEY", None):

3
pr_agent/settings/.secrets_template.toml
View File

@ -29,6 +29,9 @@ key = "" # Optional, uncomment if you want to use Cohere. Acquire through https:
[replicate] [replicate]
key = "" # Optional, uncomment if you want to use Replicate. Acquire through https://replicate.com/ key = "" # Optional, uncomment if you want to use Replicate. Acquire through https://replicate.com/
[groq]
key = "" # Acquire through https://console.groq.com/keys
[huggingface] [huggingface]
key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acquire through https://huggingface.co/docs/api-inference/quicktour key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acquire through https://huggingface.co/docs/api-inference/quicktour
api_base = "" # the base url for your huggingface inference endpoint api_base = "" # the base url for your huggingface inference endpoint