testing multi-image

.github/workflows/GHA_MultiArch.yml

@@ -0,0 +1,36 @@
+name: CI/CD Build MultiArch
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v1
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v1
+
+    - name: Login to GitHub Container Registry
+      uses: docker/login-action@v1
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.CICD_TOKEN_DataChat }}
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v2
+      with:
+        context: ./LLamaIndex/With-Mem0
+        push: true
+        platforms: linux/amd64,linux/arm64
+        tags: |
+          ghcr.io/jalcocert/data-chat:properties

.gitignore

@@ -1 +1,3 @@
-**/.env
+**/.env
+
+*_venv/

LLamaIndex-Mem0/Chat_with_md.py → LLamaIndex/With_Mem0/Chat_with_md.py

@@ -1,5 +1,6 @@
 import os
 import csv
+
 from openai import OpenAI
 from mem0 import Memory
 from llama_index.llms.anthropic import Anthropic
@@ -23,7 +24,7 @@ def __init__(self):
         # self.load_flat_examples('flat_examples.csv')
 
         # Set up Llama Index with Anthropic
-        llm = Anthropic(temperature=0.0, model='claude-3-opus-20240229')
+        llm = Anthropic(temperature=0.0,model='claude-3-5-sonnet-20240620') #claude-3-opus-20240229 #claude-3-5-sonnet-20240620
         embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5") #Embedding model will be downloaded during the first use
         Settings.llm = llm
         Settings.embed_model = embed_model

LLamaIndex-Mem0/readme.md → LLamaIndex/With_Mem0/readme.md

@@ -16,6 +16,7 @@
 
 * The **Anthropic model** isn't used directly for generating responses to user questions, it is used indirectly through the `Llama Index` for finding **relevant property documents** based on the user's previous questions.
   * [llama_index.llms.anthropic](https://docs.llamaindex.ai/en/stable/examples/llm/anthropic/)
+  * https://docs.anthropic.com/en/docs/about-claude/models
 
 * The **responses** to the user's questions are generated by the **OpenAI's GPT-4 model**. 
   * The `ask_question` method, the OpenAI client is used to create a chat completion with the GPT-4 model. The current conversation history (self.messages) is passed to the model, which generates a response. The response is then added to the conversation history.

README.md

@@ -19,4 +19,25 @@
 * PandasAI with 
     * GroqAPI
     * OpenAI ✔️
-    * SQLite DB
+    * SQLite DB
+
+```sh
+python -m venv properties_venv #create the venv | python3 if you are on linux
+
+properties_venv\Scripts\activate #activate venv (windows)
+source properties_venv/bin/activate #(linux)
+```
+
+```sh
+export GROQ_API_KEY=YOUR_API_KEY
+$env:GROQ_API_KEY="YOUR_API_KEY"
+set GROQ_API_KEY=YOUR_API_KEY
+
+export OPENAI_API_KEY=YOUR_API_KEY
+$env:OPENAI_API_KEY="YOUR_API_KEY"
+set OPENAI_API_KEY=YOUR_API_KEY
+
+export ANTHROPIC_API_KEY=YOUR_API_KEY
+$env:ANTHROPIC_API_KEY="YOUR_API_KEY"
+set ANTHROPIC_API_KEY=YOUR_API_KEY
+```