File size: 1,538 Bytes
c7db908 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import argparse
# from dataclasses import dataclass
from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
CHROMA_PATH = "chroma"
PROMPT_TEMPLATE = """
Answer the question based only on the following context:
{context}
---
Answer the question based on the above context: {question}
"""
def main():
# Create CLI.
parser = argparse.ArgumentParser()
parser.add_argument("query_text", type=str, help="The query text.")
args = parser.parse_args()
query_text = args.query_text
# Prepare the DB.
embedding_function = OpenAIEmbeddings()
db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
# Search the DB.
results = db.similarity_search_with_relevance_scores(query_text, k=3)
if len(results) == 0 or results[0][1] < 0.7:
print(f"Unable to find matching results.")
return
context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
prompt = prompt_template.format(context=context_text, question=query_text)
print(prompt)
model = ChatOpenAI()
response_text = model.predict(prompt)
sources = [doc.metadata.get("source", None) for doc, _score in results]
formatted_response = f"Response: {response_text}\nSources: {sources}"
print(formatted_response)
if __name__ == "__main__":
main()
|