SparkLLM Chat
SparkLLM chat models API by iFlyTek. For more information, seeiFlyTek Open Platform.
Basic use
"""For basic init and call"""
from langchain_community.chat_modelsimport ChatSparkLLM
from langchain_core.messagesimport HumanMessage
chat= ChatSparkLLM(
spark_app_id="<app_id>", spark_api_key="<api_key>", spark_api_secret="<api_secret>"
)
message= HumanMessage(content="Hello")
chat([message])
API Reference:ChatSparkLLM |HumanMessage
AIMessage(content='Hello! How can I help you today?')
- Get SparkLLM's app_id, api_key and api_secret fromiFlyTek SparkLLM API Console (for more info, seeiFlyTek SparkLLM Intro ), then set environment variables
IFLYTEK_SPARK_APP_ID,IFLYTEK_SPARK_API_KEYandIFLYTEK_SPARK_API_SECRETor pass parameters when creatingChatSparkLLMas the demo above.
For ChatSparkLLM with Streaming
chat= ChatSparkLLM(
spark_app_id="<app_id>",
spark_api_key="<api_key>",
spark_api_secret="<api_secret>",
streaming=True,
)
for chunkin chat.stream("Hello!"):
print(chunk.content, end="")
Hello! How can I help you today?
For v2
"""For basic init and call"""
from langchain_community.chat_modelsimport ChatSparkLLM
from langchain_core.messagesimport HumanMessage
chat= ChatSparkLLM(
spark_app_id="<app_id>",
spark_api_key="<api_key>",
spark_api_secret="<api_secret>",
spark_api_url="wss://spark-api.xf-yun.com/v2.1/chat",
spark_llm_domain="generalv2",
)
message= HumanMessage(content="Hello")
chat([message])
API Reference:ChatSparkLLM |HumanMessage
Related
- Chat modelconceptual guide
- Chat modelhow-to guides