# This env template shows how to configure Danswer for multilingual use
# In this case, it is configured for French and English
# To use it, copy it to .env in the docker_compose directory.
# Feel free to combine it with the other templates to suit your needs


# Rephrase the user query in specified languages using LLM, use comma separated values
MULTILINGUAL_QUERY_EXPANSION="English, French"

# A recent MIT license multilingual model: https://huggingface.co/intfloat/multilingual-e5-small
DOCUMENT_ENCODER_MODEL="intfloat/multilingual-e5-small"

# The model above is trained with the following prefix for queries and passages to improve retrieval
# by letting the model know which of the two type is currently being embedded
ASYM_QUERY_PREFIX="query: "
ASYM_PASSAGE_PREFIX="passage: "

# Depends model by model, the one shown above is tuned with this as True
NORMALIZE_EMBEDDINGS="True"

# Use LLM to determine if chunks are relevant to the query
# May not work well for languages that do not have much training data in the LLM training set
# If using a common language like Spanish, French, Chinese, etc. this can be kept turned on
DISABLE_LLM_CHUNK_FILTER="True"

# The default reranking models are English first
# There are no great quality French/English reranking models currently so turning this off
ENABLE_RERANKING_ASYNC_FLOW="False"
ENABLE_RERANKING_REAL_TIME_FLOW="False"

# Enables fine-grained embeddings for better retrieval
# At the cost of indexing speed (~5x slower), query time is same speed
# Since reranking is turned off and multilingual retrieval is generally harder
# it is advised to turn this one on
ENABLE_MINI_CHUNK="True"

# Using a stronger LLM will help with multilingual tasks
# Since documents may be in multiple languages, and there are additional instructions to respond
# in the user query's language, it is advised to use the best model possible
GEN_AI_MODEL_VERSION="gpt-4"