File size: 1,608 Bytes
c47212f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
54
55
import argparse
from langchain_community.vectorstores import Chroma  
from langchain.prompts import ChatPromptTemplate
from langchain_community.llms.ollama import Ollama

from get_embedding_function import get_embedding_function

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
    # query_rag(query_text)
    query_rag(input( "Enter your query: "))


def query_rag(query_text: str):
    # Prepare the DB.
    embedding_function = get_embedding_function()
    db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)

    # Search the DB.
    results = db.similarity_search_with_score(query_text, k=5)

    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 = Ollama(model="mistral")
    response_text = model.invoke(prompt)

    sources = [doc.metadata.get("id", None) for doc, _score in results]
    formatted_response = f"Response: {response_text}\nSources: {sources}"
    print(formatted_response)
    return response_text


if __name__ == "__main__":
    main()