baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

add demo video

Browse source
This commit is contained in:
Michael Chiang 2023-08-11 08:58:57 -07:00
parent e863066144
commit 155c1640f1
2 changed files with 10 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
examples/privategpt/README.md
View file

@ -1,6 +1,8 @@
# privateGPT with Llama 2 Uncensored # PrivateGPT with Llama 2 uncensored
> Note: this example is a simplified version of [PrivateGPT](https://github.com/imartinez/privateGPT) that works with Llama 2 Uncensored. https://github.com/jmorganca/ollama/assets/3325447/20cf8ec6-ff25-42c6-bdd8-9be594e3ce1b
> Note: this example is a simplified version of [PrivateGPT](https://github.com/imartinez/privateGPT) that works with Llama 2 Uncensored. All credit for PrivateGPT goes to Iván Martínez who is the creator of it.
### Setup ### Setup
@ -23,7 +25,7 @@ Pull the model you'd like to use:
ollama pull llama2-uncensored ollama pull llama2-uncensored
``` ```
### Getting WeWork's latest quarterly report ### Getting WeWork's latest quarterly earnings report (10-Q)
``` ```
mkdir source_documents mkdir source_documents

6
examples/privategpt/privateGPT.py
View file

@ -3,12 +3,15 @@ from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings from langchain.embeddings import HuggingFaceEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.vectorstores import Chroma from langchain.vectorstores import Chroma
from langchain.llms import GPT4All, Ollama from langchain.llms import Ollama
import os import os
import argparse import argparse
import time import time
model = os.environ.get("MODEL", "llama2-uncensored") model = os.environ.get("MODEL", "llama2-uncensored")
# For embeddings model, the example uses a sentence-transformers model
# https://www.sbert.net/docs/pretrained_models.html
# "The all-mpnet-base-v2 model provides the best quality, while all-MiniLM-L6-v2 is 5 times faster and still offers good quality."
embeddings_model_name = os.environ.get("EMBEDDINGS_MODEL_NAME", "all-MiniLM-L6-v2") embeddings_model_name = os.environ.get("EMBEDDINGS_MODEL_NAME", "all-MiniLM-L6-v2")
persist_directory = os.environ.get("PERSIST_DIRECTORY", "db") persist_directory = os.environ.get("PERSIST_DIRECTORY", "db")
target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4)) target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
@ -44,7 +47,6 @@ def main():
# Print the result # Print the result
print("\n\n> Question:") print("\n\n> Question:")
print(query) print(query)
print(f"\n> Answer (took {round(end - start, 2)} s.):")
print(answer) print(answer)
# Print the relevant sources used for the answer # Print the relevant sources used for the answer