Correcting the retrieval of relevant documents
This commit is contained in:
@@ -77,6 +77,7 @@ class Config(object):
|
||||
```{text}```"""
|
||||
GPT3_5_SUMMARY_TEMPLATE = """Write a concise summary of the text in {language}. The text is delimited between triple backquotes.
|
||||
```{text}```"""
|
||||
|
||||
GPT4_RAG_TEMPLATE = """Answer the question based on the following context, delimited between triple backquotes.
|
||||
Use the following {language} in your communication, and cite the sources used.
|
||||
If the question cannot be answered using the given context, say "I have insufficient information to answer this question."
|
||||
@@ -92,6 +93,17 @@ class Config(object):
|
||||
Question:
|
||||
{question}"""
|
||||
|
||||
GPT4_HISTORY_TEMPLATE = """You are a helpful assistant that details a question based on a previous context,
|
||||
in such a way that the question is understandable without the previous context.
|
||||
The context is a conversation history, with the HUMAN asking questions, the AI answering questions.
|
||||
The history is delimited between triple backquotes.
|
||||
Your answer by stating the question in {language}.
|
||||
History:
|
||||
```{history}```
|
||||
Question to be detailed:
|
||||
{question}"""
|
||||
|
||||
|
||||
# SocketIO settings
|
||||
# SOCKETIO_ASYNC_MODE = 'threading'
|
||||
SOCKETIO_ASYNC_MODE = 'gevent'
|
||||
|
||||
Reference in New Issue
Block a user