Update README for OLLAMA version

README.md

@@ -1 +1,35 @@
 # rag-tutorial-v2
+
+## Running with OLLAMA
+
+1. Install the following packages:
+```shell
+$ pip3 install langchain
+$ pip3 install chromadb
+$ pip3 install pypdf
+$ pip3 install pytest
+$ pip3 install langchain-community
+$ pip3 install -U langchain-chroma
+```
+
+2. Make sure you have ollama on your machine by checking out the instructions in [Ollama Github](https://github.com/ollama/ollama)
+
+3. Once ollama has been downloaded, start the server in another terminal window:
+```shell
+$ ollama serve
+```
+
+4. Pull the models needed:
+```shell
+$ ollama pull nomic-embed-text
+$ ollama pull mistral
+```
+
+5. Run the program. Below is an example:
+```shell
+$ python3 query_data.py "how much total money does a player start with in Monopoly?"
+```
+
+The return answer should be shown in the terminal.
+
+

get_embedding_function.py

@@ -3,8 +3,8 @@
 
 
 def get_embedding_function():
-    embeddings = BedrockEmbeddings(
-        credentials_profile_name="default", region_name="us-east-1"
-    )
-    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    #embeddings = BedrockEmbeddings(
+    #    credentials_profile_name="default", region_name="us-east-1"
+    #)
+    embeddings = OllamaEmbeddings(model="nomic-embed-text")
     return embeddings

query_data.py

@@ -1,5 +1,6 @@
 import argparse
-from langchain.vectorstores.chroma import Chroma
+#from langchain.vectorstores.chroma import Chroma
+from langchain_chroma import Chroma
 from langchain.prompts import ChatPromptTemplate
 from langchain_community.llms.ollama import Ollama