add demo video

examples/privategpt/README.md

@@ -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
 
@@ -23,11 +25,11 @@ Pull the model you'd like to use:
 ollama pull llama2-uncensored
 ```
 
-### Getting WeWork's latest quarterly report
+### Getting WeWork's latest quarterly earnings report (10-Q)
 
 ```
 mkdir source_documents
-curl https://d18rn0p25nwr6d.cloudfront.net/CIK-0001813756/975b3e9b-268e-4798-a9e4-2a9a7c92dc10.pdf  -o source_documents/wework.pdf
+curl https://d18rn0p25nwr6d.cloudfront.net/CIK-0001813756/975b3e9b-268e-4798-a9e4-2a9a7c92dc10.pdf -o source_documents/wework.pdf
 ```
 
 ### Ingesting data

examples/privategpt/privateGPT.py

@@ -3,12 +3,15 @@ from langchain.chains import RetrievalQA
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.vectorstores import Chroma
-from langchain.llms import GPT4All, Ollama
+from langchain.llms import Ollama
 import os
 import argparse
 import time
 
 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")
 persist_directory = os.environ.get("PERSIST_DIRECTORY", "db")
 target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
@@ -44,7 +47,6 @@ def main():
         # Print the result
         print("\n\n> Question:")
         print(query)
-        print(f"\n> Answer (took {round(end - start, 2)} s.):")
         print(answer)
 
         # Print the relevant sources used for the answer