kartik-mem0
2ef6291307
The Python Together LLM and embedder ignored TOGETHER_API_BASE, unlike their TypeScript siblings, so users behind a gateway or proxy could not redirect Together traffic. Add together_base_url to a new TogetherConfig (LLM side) and to BaseEmbedderConfig (embedder side, matching the existing openai_base_url/huggingface_base_url pattern), and resolve base_url with explicit config value > TOGETHER_API_BASE env var > hardcoded default in both mem0/llms/together.py and mem0/embeddings/together.py. Also register TogetherConfig in LlmFactory.provider_to_class so config dicts routed through Memory pick it up. Closes #6587
114 lines
4.2 KiB
Python
114 lines
4.2 KiB
Python
import json
|
|
import os
|
|
from typing import Dict, List, Optional, Union
|
|
|
|
try:
|
|
from together import Together
|
|
except ImportError:
|
|
raise ImportError("The 'together' library is required. Please install it using 'pip install together'.")
|
|
|
|
from mem0.configs.llms.base import BaseLlmConfig
|
|
from mem0.configs.llms.together import TogetherConfig
|
|
from mem0.llms.base import LLMBase
|
|
from mem0.memory.utils import extract_json
|
|
|
|
|
|
class TogetherLLM(LLMBase):
|
|
def __init__(self, config: Optional[Union[BaseLlmConfig, TogetherConfig, Dict]] = None):
|
|
# Convert to TogetherConfig if needed
|
|
if config is None:
|
|
config = TogetherConfig()
|
|
elif isinstance(config, dict):
|
|
config = TogetherConfig(**config)
|
|
elif isinstance(config, BaseLlmConfig) and not isinstance(config, TogetherConfig):
|
|
# Convert BaseLlmConfig to TogetherConfig
|
|
config = TogetherConfig(
|
|
model=config.model,
|
|
temperature=config.temperature,
|
|
api_key=config.api_key,
|
|
max_tokens=config.max_tokens,
|
|
top_p=config.top_p,
|
|
top_k=config.top_k,
|
|
enable_vision=config.enable_vision,
|
|
vision_details=config.vision_details,
|
|
http_client_proxies=config.http_client_proxies,
|
|
)
|
|
|
|
super().__init__(config)
|
|
|
|
if not self.config.model:
|
|
self.config.model = "MiniMaxAI/MiniMax-M3"
|
|
|
|
api_key = self.config.api_key or os.getenv("TOGETHER_API_KEY")
|
|
base_url = self.config.together_base_url or os.getenv("TOGETHER_API_BASE") or "https://api.together.ai/v1"
|
|
self.client = Together(api_key=api_key, base_url=base_url)
|
|
|
|
def _parse_response(self, response, tools):
|
|
"""
|
|
Process the response based on whether tools are used or not.
|
|
|
|
Args:
|
|
response: The raw response from API.
|
|
tools: The list of tools provided in the request.
|
|
|
|
Returns:
|
|
str or dict: The processed response.
|
|
"""
|
|
if tools:
|
|
processed_response = {
|
|
"content": response.choices[0].message.content,
|
|
"tool_calls": [],
|
|
}
|
|
|
|
if response.choices[0].message.tool_calls:
|
|
for tool_call in response.choices[0].message.tool_calls:
|
|
processed_response["tool_calls"].append(
|
|
{
|
|
"name": tool_call.function.name,
|
|
"arguments": json.loads(extract_json(tool_call.function.arguments)),
|
|
}
|
|
)
|
|
|
|
return processed_response
|
|
else:
|
|
return response.choices[0].message.content
|
|
|
|
def generate_response(
|
|
self,
|
|
messages: List[Dict[str, str]],
|
|
response_format=None,
|
|
tools: Optional[List[Dict]] = None,
|
|
tool_choice: str = "auto",
|
|
**kwargs,
|
|
):
|
|
"""
|
|
Generate a response based on the given messages using TogetherAI.
|
|
|
|
Args:
|
|
messages (list): List of message dicts containing 'role' and 'content'.
|
|
response_format (str or object, optional): Format of the response. Defaults to "text".
|
|
tools (list, optional): List of tools that the model can call. Defaults to None.
|
|
tool_choice (str, optional): Tool choice method. Defaults to "auto".
|
|
**kwargs: Additional provider-specific parameters forwarded to the Together
|
|
client (matches the ``LLMBase.generate_response`` contract).
|
|
|
|
Returns:
|
|
str: The generated response.
|
|
"""
|
|
params = {
|
|
"model": self.config.model,
|
|
"messages": messages,
|
|
"temperature": self.config.temperature,
|
|
"max_tokens": self.config.max_tokens,
|
|
"top_p": self.config.top_p,
|
|
}
|
|
params.update(kwargs)
|
|
if response_format:
|
|
params["response_format"] = response_format
|
|
if tools: # TODO: Remove tools if no issues found with new memory addition logic
|
|
params["tools"] = tools
|
|
params["tool_choice"] = tool_choice
|
|
|
|
response = self.client.chat.completions.create(**params)
|
|
return self._parse_response(response, tools)
|