mirror of
https://github.com/arc53/DocsGPT.git
synced 2025-11-29 16:43:16 +00:00
3f7de867cc
* feat: Implement model registry and capabilities for multi-provider support - Added ModelRegistry to manage available models and their capabilities. - Introduced ModelProvider enum for different LLM providers. - Created ModelCapabilities dataclass to define model features. - Implemented methods to load models based on API keys and settings. - Added utility functions for model management in model_utils.py. - Updated settings.py to include provider-specific API keys. - Refactored LLM classes (Anthropic, OpenAI, Google, etc.) to utilize new model registry. - Enhanced utility functions to handle token limits and model validation. - Improved code structure and logging for better maintainability. * feat: Add model selection feature with API integration and UI component * feat: Add model selection and default model functionality in agent management * test: Update assertions and formatting in stream processing tests * refactor(llm): Standardize model identifier to model_id * fix tests --------- Co-authored-by: Alex <a@tushynski.me>
73 lines
2.2 KiB
Python
73 lines
2.2 KiB
Python
from anthropic import AI_PROMPT, Anthropic, HUMAN_PROMPT
|
|
|
|
from application.core.settings import settings
|
|
from application.llm.base import BaseLLM
|
|
|
|
|
|
class AnthropicLLM(BaseLLM):
|
|
|
|
def __init__(self, api_key=None, user_api_key=None, base_url=None, *args, **kwargs):
|
|
|
|
super().__init__(*args, **kwargs)
|
|
self.api_key = api_key or settings.ANTHROPIC_API_KEY or settings.API_KEY
|
|
self.user_api_key = user_api_key
|
|
|
|
# Use custom base_url if provided
|
|
if base_url:
|
|
self.anthropic = Anthropic(api_key=self.api_key, base_url=base_url)
|
|
else:
|
|
self.anthropic = Anthropic(api_key=self.api_key)
|
|
|
|
self.HUMAN_PROMPT = HUMAN_PROMPT
|
|
self.AI_PROMPT = AI_PROMPT
|
|
|
|
def _raw_gen(
|
|
self,
|
|
baseself,
|
|
model,
|
|
messages,
|
|
stream=False,
|
|
tools=None,
|
|
max_tokens=300,
|
|
**kwargs,
|
|
):
|
|
context = messages[0]["content"]
|
|
user_question = messages[-1]["content"]
|
|
prompt = f"### Context \n {context} \n ### Question \n {user_question}"
|
|
if stream:
|
|
return self.gen_stream(model, prompt, stream, max_tokens, **kwargs)
|
|
completion = self.anthropic.completions.create(
|
|
model=model,
|
|
max_tokens_to_sample=max_tokens,
|
|
stream=stream,
|
|
prompt=f"{self.HUMAN_PROMPT} {prompt}{self.AI_PROMPT}",
|
|
)
|
|
return completion.completion
|
|
|
|
def _raw_gen_stream(
|
|
self,
|
|
baseself,
|
|
model,
|
|
messages,
|
|
stream=True,
|
|
tools=None,
|
|
max_tokens=300,
|
|
**kwargs,
|
|
):
|
|
context = messages[0]["content"]
|
|
user_question = messages[-1]["content"]
|
|
prompt = f"### Context \n {context} \n ### Question \n {user_question}"
|
|
stream_response = self.anthropic.completions.create(
|
|
model=model,
|
|
prompt=f"{self.HUMAN_PROMPT} {prompt}{self.AI_PROMPT}",
|
|
max_tokens_to_sample=max_tokens,
|
|
stream=True,
|
|
)
|
|
|
|
try:
|
|
for completion in stream_response:
|
|
yield completion.completion
|
|
finally:
|
|
if hasattr(stream_response, "close"):
|
|
stream_response.close()
|