Update rag.py

rag.py

@@ -1,5 +1,18 @@
 # rag.py
 # https://github.com/vndee/local-rag-example/blob/main/rag.py
+# ADAPTED TO USE HF LLM INSTEAD OF OLLAMA self.model = ChatOllama(model="mistral") BY J. BOURS 01-03-2024
+# EVERNOTE:
+# https://www.evernote.com/shard/s313/nl/41973486/282c6fc8-9ed5-a977-9895-1eb23941bb4c?title=REQUIREMENTS%20FOR%20A%20LITERATURE%20BASED%20RESEARCH%20LBR%20SYSTEM%20-%20FUNCTIONAL%20AND%20TECHNICAL%20REQUIREMENTS%20-%20ALEXANDER%20UNZICKER%20-%2026-02-2024
+#
+# mistralai/Mistral-7B-v0.1 · Hugging Face 
+# https://huggingface.co/mistralai/Mistral-7B-v0.1?library=true
+#
+# Load model directly
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+#
+# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
+# model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+
 
 from langchain.vectorstores import Chroma
 from langchain.chat_models import ChatOllama
@@ -11,6 +24,9 @@ from langchain.schema.runnable import RunnablePassthrough
 from langchain.prompts import PromptTemplate
 from langchain.vectorstores.utils import filter_complex_metadata
 
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
 
 class ChatPDF:
     vector_store = None
@@ -18,7 +34,18 @@ class ChatPDF:
     chain = None
 
     def __init__(self):
-        self.model = ChatOllama(model="mistral")
+        # self.model = ChatOllama(model="mistral") # ORIGINAL
+        # mistralai/Mistral-7B-v0.1 · Hugging Face 
+        # https://huggingface.co/mistralai/Mistral-7B-v0.1?library=true
+        #
+        # Load model directly
+        # from transformers import AutoTokenizer, AutoModelForCausalLM
+        #
+        # tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
+        # model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+        tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
+        self.model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1") 
+
         self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=100)
         self.prompt = PromptTemplate.from_template(
             """