SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 20:12:55 +01:00
Code Issues Projects Releases Packages Activity

.env + LlamaCpp + PDF/CSV + Ingest All

Browse source 
.env

Added an env file to make configuration easier

LlamaCpp

Added support for LlamaCpp in .env (MODEL_TYPE=LlamaCpp)

PDF/CSV

Added support for PDF and CSV files.

Ingest All

All files in source_documents will automatically get stored in vector store based on their file type when running ingest, no longer need a path argument.
This commit is contained in:
alxspiker 2023-05-11 14:24:39 -06:00
parent 60225698b6
commit 52ae6c0866
4 changed files with 49 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

22
privateGPT.py
View file

@ -2,17 +2,31 @@ from langchain.chains import RetrievalQA
from langchain.embeddings import LlamaCppEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.vectorstores import Chroma
from langchain.llms import GPT4All
from langchain.llms import GPT4All, LlamaCpp
import os
llama_embeddings_model = os.environ.get("LLAMA_EMBEDDINGS_MODEL")
persist_directory = os.environ.get('PERSIST_DIRECTORY')
model_type = os.environ.get('MODEL_TYPE')
model_path = os.environ.get('MODEL_PATH')
model_n_ctx = os.environ.get('MODEL_N_CTX')
def main():
# Load stored vectorstore
llama = LlamaCppEmbeddings(model_path="./models/ggml-model-q4_0.bin")
persist_directory = 'db'
llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx)
db = Chroma(persist_directory=persist_directory, embedding_function=llama)
retriever = db.as_retriever()
# Prepare the LLM
callbacks = [StreamingStdOutCallbackHandler()]
llm = GPT4All(model='./models/ggml-gpt4all-j-v1.3-groovy.bin', backend='gptj', callbacks=callbacks, verbose=False)
match model_type:
case "LlamaCpp":
llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, callbacks=callbacks, verbose=False)
case "GPT4All":
llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
case _default:
print(f"Model {model_type} not supported!")
exit;
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
# Interactive questions and answers
while True: