wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update NimLLMService docstrings

Browse Source
This commit is contained in:
Mark Backman
2025-06-26 10:47:26 -04:00
parent 79cca05e43
commit 56e2b006f5
1 changed files with 14 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/pipecat/services/nim/llm.py
View File

@@ -4,6 +4,12 @@
# SPDX-License-Identifier: BSD 2-Clause License # SPDX-License-Identifier: BSD 2-Clause License
# #
"""NVIDIA NIM API service implementation.
This module provides a service for interacting with NVIDIA's NIM (NVIDIA Inference
Microservice) API while maintaining compatibility with the OpenAI-style interface.
"""
from pipecat.metrics.metrics import LLMTokenUsage from pipecat.metrics.metrics import LLMTokenUsage
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.openai.llm import OpenAILLMService from pipecat.services.openai.llm import OpenAILLMService
@@ -17,10 +23,10 @@ class NimLLMService(OpenAILLMService):
in token usage reporting between NIM (incremental) and OpenAI (final summary). in token usage reporting between NIM (incremental) and OpenAI (final summary).
Args: Args:
api_key (str): The API key for accessing NVIDIA's NIM API api_key: The API key for accessing NVIDIA's NIM API.
base_url (str, optional): The base URL for NIM API. Defaults to "https://integrate.api.nvidia.com/v1" base_url: The base URL for NIM API. Defaults to "https://integrate.api.nvidia.com/v1".
model (str, optional): The model identifier to use. Defaults to "nvidia/llama-3.1-nemotron-70b-instruct" model: The model identifier to use. Defaults to "nvidia/llama-3.1-nemotron-70b-instruct".
**kwargs: Additional keyword arguments passed to OpenAILLMService **kwargs: Additional keyword arguments passed to OpenAILLMService.
""" """
def __init__( def __init__(
@@ -47,8 +53,8 @@ class NimLLMService(OpenAILLMService):
them once at the end of processing. them once at the end of processing.
Args: Args:
context (OpenAILLMContext): The context to process, containing messages context: The context to process, containing messages and other information
and other information needed for the LLM interaction. needed for the LLM interaction.
""" """
# Reset all counters and flags at the start of processing # Reset all counters and flags at the start of processing
self._prompt_tokens = 0 self._prompt_tokens = 0
@@ -79,8 +85,8 @@ class NimLLMService(OpenAILLMService):
The final accumulated totals are reported at the end of processing. The final accumulated totals are reported at the end of processing.
Args: Args:
tokens (LLMTokenUsage): The token usage metrics for the current chunk tokens: The token usage metrics for the current chunk of processing,
of processing, containing prompt_tokens and completion_tokens counts. containing prompt_tokens and completion_tokens counts.
""" """
# Only accumulate metrics during active processing # Only accumulate metrics during active processing
if not self._is_processing: if not self._is_processing: