Chat Engine #15418
Unanswered
d3buggerdan
asked this question in
Q&A
Chat Engine
#15418
Replies: 1 comment 4 replies
-
To create a chat engine with the best context mode and include chat history, you can use the following code: # Assuming `index` is already created and configured
chat_engine = index.as_chat_engine(chat_mode="best", verbose=True)
# To include chat history, you can initialize the conversation with some existing history
from llama_index.core.llms import ChatMessage, MessageRole
custom_chat_history = [
ChatMessage(
role=MessageRole.USER,
content="Hello assistant, we are having an insightful discussion about Paul Graham today.",
),
ChatMessage(role=MessageRole.ASSISTANT, content="Okay, sounds good."),
]
# Assuming `query_engine` is already created and configured
chat_engine = CondenseQuestionChatEngine.from_defaults(
query_engine=query_engine,
chat_history=custom_chat_history,
verbose=True,
)
# Now you can have a conversation with your data
response = chat_engine.chat("Tell me a joke.")
print(response) This code sets up a chat engine with the "best" context mode and includes some initial chat history. For more detailed information, you can refer to the LlamaIndex Chat Engines documentation [1][2]. |
Beta Was this translation helpful? Give feedback.
4 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
@dosu
How can i make this with the best or context mode and have chat history.
Initialize custom chat history
custom_chat_history = [
]
Create the chat engine using the low-level API
chat_engine = CondenseQuestionChatEngine.from_defaults(
query_engine=query_engine,
#condense_question_prompt=custom_prompt,
chat_history=custom_chat_history,
verbose=True,)
Beta Was this translation helpful? Give feedback.
All reactions