Add docs for ollama setup (#122)

* docs: update README and .env.example for Ollama model support

* docs: update name for uniformity

* docs: update README to include instructions for downloading model weights

* chore: update .env.example

---------

Signed-off-by: Palaniappan R <[email protected]>

Author: palaniappan-r

README.md

@@ -1,4 +1,4 @@
-# OR-Assistant
+# ORAssistant
 
 [![ORAssistant CI](https://github.com/The-OpenROAD-Project/ORAssistant/actions/workflows/ci.yaml/badge.svg)](https://github.com/The-OpenROAD-Project/ORAssistant/actions/workflows/ci.yaml)
 

backend/.env.example

@@ -6,8 +6,15 @@ SEARCH_K=5
 CHUNK_SIZE=2000
 CHUNK_OVERLAP=200
 
+# Choose between 'gemini' or 'ollama'
 LLM_MODEL="gemini"
-GOOGLE_GEMINI="1.5_flash" #1_pro or 1.5_flash or 1.5_pro
+
+# Specify model name if using Ollama
+OLLAMA_MODEL=""
+
+# Set Google Gemini model version
+GOOGLE_GEMINI="1.5_flash"
+
 LLM_TEMP=1
 
 EMBEDDINGS_TYPE="GOOGLE_VERTEXAI"

backend/README.md

@@ -46,6 +46,21 @@ This key is used to access the various google cloud functions.
 
 **NOTE**: The user might need billing to be set up on google cloud account and make sure to name the file as `credentials.json`  as this would be ignored by `.git` and wouldn't be exposed on Github
 
+### Running ORAssistant with a Local Ollama Model
+
+ORAssistant supports running locally hosted Ollama models for inference. Follow these steps to set it up:
+
+#### 1. Install Ollama  
+- Visit [Ollama's installation page](https://ollama.com/download) and follow the installation instructions for your system.
+
+#### 2. Configure ORAssistant to Use Ollama  
+- In your `.env` file, set:  
+  ```bash
+  LLM_MODEL="ollama"
+  OLLAMA_MODEL="<model_name>"
+
+Ensure Ollama is running locally before starting ORAssistant. Make sure the model weights are available by downloading them first with `ollama pull <model_name>`.
+
 ### Setting Up LangChain Variables
 
 There are 4 variables that needs to be set up