How to make Model answer only from my docs

[TheJokerBG]

Hi, i'm useing LangChain to ingest a TXT database in to a vector one and feed it to an LLM model.
Can i put a parameter so the model returns answers only if they are present in the DB and not from the pretrained info ?

[dosubot[bot]]

🤖

Hi there,

Yes, you can configure LangChain to return answers only from the ingested TXT database, rather than using its pre-trained information. This can be achieved by using the QUESTION_PROMPT and COMBINE_PROMPT templates defined in the map_reduce_prompt.py file.

Here is the relevant code:

QUESTION_PROMPT = PromptTemplate(
    template=question_prompt_template, input_variables=["context", "question"]
)

combine_prompt_template = """Given the following extracted parts of a long document and a question, create a final answer with references ("SOURCES"). 
If you don't know the answer, just say that you don't know. Don't try to make up an answer.
ALWAYS return a "SOURCES" part in your answer.
QUESTION: {question}
=========
{summaries}
=========
FINAL ANSWER:"""
COMBINE_PROMPT = PromptTemplate(
    template=combine_prompt_template, input_variables=["summaries", "question"]
)

In this way, LangChain ensures that the language model only returns answers that are present in the ingested TXT database, rather than using its pre-trained information. You can find more details in the map_reduce_prompt.py file.

As for the process of ingesting a TXT database into a vector one in LangChain, here is a sample code snippet:

from langchain.embedding.openai import OpenAIEmbeddings
from langchain.vectorstores.epsilla import Epsilla
from pyepsilla import vectordb

# Initialize the Epsilla client
client = vectordb.Client()
vectorstore = Epsilla(
    client=client,
    embeddings=OpenAIEmbeddings(),
    db_path="/tmp/vectorstore",
    db_name="langchain_store"
)

# Read the texts from the TXT database
with open('database.txt', 'r') as file:
    texts = file.readlines()

# Add the texts to the vector store
vectorstore.add_texts(texts)

In this example, the OpenAIEmbeddings class is used for embeddings. The texts are read from a TXT file named 'database.txt'. The add_texts method is then used to add these texts to the vector store.

I hope this helps! Let me know if you have any other questions.

Sources

• Issue: Not answering questions out of context using RetrievalQA Chain and ConversationalChatAgent
• libs/langchain/langchain/chains/qa_with_sources/map_reduce_prompt.py
• libs/langchain/langchain/vectorstores/typesense.py
• libs/langchain/langchain/vectorstores/tencentvectordb.py
• libs/langchain/langchain/vectorstores/elasticsearch.py
• libs/langchain/langchain/vectorstores/epsilla.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.