mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-11-04 03:39:31 +00:00
d048bb5352
* init * Change question * Add TODO comment * Addressing feedback * Add local folder option. Move additional functions inside haystack.utils for easier imports * Apply Daria's review suggestions Co-authored-by: Daria Fokina <daria.fokina@deepset.ai> * Add integration test * change string formatting Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com> * Add outputparser to HF * Exclude anthropic test --------- Co-authored-by: Daria Fokina <daria.fokina@deepset.ai> Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
35 lines
1.5 KiB
Python
35 lines
1.5 KiB
Python
from haystack.document_stores import InMemoryDocumentStore
|
|
from haystack.utils import build_pipeline, add_example_data, print_answers
|
|
|
|
|
|
def getting_started(provider, API_KEY):
|
|
"""
|
|
This getting_started example shows you how to use LLMs with your data with a technique called Retrieval Augmented Generation - RAG.
|
|
|
|
:param provider: We are model agnostic :) Here, you can choose from: "anthropic", "cohere", "huggingface", and "openai".
|
|
:param API_KEY: The API key matching the provider.
|
|
|
|
"""
|
|
|
|
# We support many different databases. Here we load a simple and lightweight in-memory database.
|
|
document_store = InMemoryDocumentStore(use_bm25=True)
|
|
|
|
# Pipelines are the main abstraction in Haystack, they connect components like LLMs and databases.
|
|
pipeline = build_pipeline(provider, API_KEY, document_store)
|
|
|
|
# Download and add Game of Thrones TXT articles to Haystack's database.
|
|
# You can also provide a folder with your local documents.
|
|
# You might need to install additional dependencies - look inside the function for more information.
|
|
add_example_data(document_store, "data/GoT_getting_started")
|
|
|
|
# Ask a question on the data you just added.
|
|
result = pipeline.run(query="Who is the father of Arya Stark?")
|
|
|
|
# For details such as which documents were used to generate the answer, look into the <result> object.
|
|
print_answers(result, details="medium")
|
|
return result
|
|
|
|
|
|
if __name__ == "__main__":
|
|
getting_started(provider="openai", API_KEY="ADD KEY HERE")
|