pip install -r requirements.txt
Make sure to have Ollama running on your system from https://ollama.ai
ollama pull mistral
mkdir source_documents
python ingest.py
Output should look like this:
Creating new vectorstore
Loading documents from source_documents
Loading new documents: 100%|██████████████████████| 1/1 [00:01<00:00, 1.99s/it]
Loaded 235 new documents from source_documents
Split into 1268 chunks of text (max. 500 tokens each)
Creating embeddings. May take some minutes...
Ingestion complete! You can now run pdf-Ollama.py to query your documents
python pdf-Ollama.py
Enter a query: How many locations does WeWork have?
ollama pull llama2:13b
MODEL=llama2:13b python privateGPT.py
Put any and all your files into the source_documents
directory
The supported extensions are:
.csv
: CSV,.docx
: Word Document,.doc
: Word Document,.enex
: EverNote,.eml
: Email,.epub
: EPub,.html
: HTML File,.md
: Markdown,.msg
: Outlook Message,.odt
: Open Document Text,.pdf
: Portable Document Format (PDF),.pptx
: PowerPoint Document,.ppt
: PowerPoint Document,.txt
: Text file (UTF-8),
This code is generated from the Pdf-Chat project by PromptEngineer48