From 48123f7debc569c25332bbd54b7b8a3686d7f115 Mon Sep 17 00:00:00 2001
From: Dobromir Popov <dobromir.popov@gateway.one>
Date: Wed, 6 Mar 2024 11:50:19 +0200
Subject: [PATCH] store

---
 agent-android/prompts.txt |  7 +++++
 store-py/notes.md         | 60 +++++++++++++++++++++++++++++++++++++++
 store-py/store.py         | 39 +++++++++++++++++++++++++
 3 files changed, 106 insertions(+)
 create mode 100644 agent-android/prompts.txt
 create mode 100644 store-py/notes.md
 create mode 100644 store-py/store.py

diff --git a/agent-android/prompts.txt b/agent-android/prompts.txt
new file mode 100644
index 0000000..efd1f2b
--- /dev/null
+++ b/agent-android/prompts.txt
@@ -0,0 +1,7 @@
+you're in a shell console at a root folder of a new software project. we use vscode.
+let's create a mobile app (prioritize android, and plan to also support iOS) which will send the audio input to tts llm 
+plan for the following extesion features in the future:
+ - ability to listen in the background for a wake word and send the following voice command
+ - ability to listen on hardware button press, or O buttton hold or other android fast access shortcut intent
+ 
+ 
\ No newline at end of file
diff --git a/store-py/notes.md b/store-py/notes.md
new file mode 100644
index 0000000..484bc1e
--- /dev/null
+++ b/store-py/notes.md
@@ -0,0 +1,60 @@
+
+<<
+using python, create a new project that will utilize a vector store database to create interlinked vector space knowledge graph as a "memory" function. It will be used by a realtime LLM to store and retrieve knowledge>>
+#Environment Setup
+cd vector_knowledge_graph
+python -m venv venv
+source venv/bin/activate
+pip install fastapi uvicorn openai psycopg2-binary sqlalchemy
+
+
+#Create a Database: Create a new PostgreSQL database.
+CREATE EXTENSION vector;
+CREATE TABLE knowledge (
+    id SERIAL PRIMARY KEY,
+    embedding vector(1536) NOT NULL, -- assuming 512 dimensions for embeddings; openai uses 1536
+    metadata JSONB
+);
+CREATE INDEX ON knowledge USING ivfflat (embedding);
+
+#Application Code
+<!-- FastAPI Setup (app/api/main.py): Initialize FastAPI with a simple endpoint for testing. -->
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.get("/")
+async def read_root():
+    return {"Hello": "World"}
+Database Client (app/vector_db/client.py): Implement a simple client for connecting to the database and inserting/fetching vectors.
+
+python
+Copy code
+import psycopg2
+from psycopg2.extras import Json
+
+def insert_embedding(embedding, metadata):
+    conn = psycopg2.connect("dbname=your_db user=your_user")
+    cur = conn.cursor()
+    cur.execute("INSERT INTO knowledge (embedding, metadata) VALUES (%s, %s)", (embedding, Json(metadata)))
+    conn.commit()
+    cur.close()
+    conn.close()
+
+def search_embedding(embedding):
+    conn = psycopg2.connect("dbname=your_db user=your_user")
+    cur = conn.cursor()
+    cur.execute("SELECT id, metadata FROM knowledge ORDER BY embedding <-> %s LIMIT 5", (embedding,))
+    results = cur.fetchall()
+    cur.close()
+    conn.close()
+    return results
+5. LLM Integration
+At this stage, we'll need to implement the logic to interact with OpenAI's API to generate and process embeddings. Since this involves using OpenAI's services, ensure you have an API key and have agreed to their terms of use.
+
+6. Running the Application
+With the basic components in place, you can start the FastAPI application using uvicorn:
+
+bash
+Copy code
+uvicorn app.api.main:app --reload
\ No newline at end of file
diff --git a/store-py/store.py b/store-py/store.py
new file mode 100644
index 0000000..dca89bf
--- /dev/null
+++ b/store-py/store.py
@@ -0,0 +1,39 @@
+import faiss
+import numpy as np
+
+# Define the knowledge graph schema
+entities = ['Alice', 'Bob', 'Charlie']
+relationships = [('Alice', 'friend', 'Bob'), ('Alice', 'friend', 'Charlie')]
+
+# Create the database schema
+db = faiss.Database('knowledge_graph.db')
+
+db.create_table('entities', entities)
+db.create_table('relationships', relationships)
+
+# Implement the knowledge graph embedding
+model = Word2Vec(sentences=['Alice is friends with Bob and Charlie'], dim=100)
+
+# Store the knowledge graph in the database
+for entity in entities:
+    db.insert('entities', entity)
+for relationship in relationships:
+    db.insert('relationships', relationship)
+
+# Implement the LLM
+llm = LanguageModel(model)
+
+# Integrate the knowledge graph embedding with the LLM
+def get_entity_vector(entity):
+    entity_vector = np.array(db.get('entities', entity))
+    return entity_vector
+
+def get_relationship_vector(relationship):
+    relationship_vector = np.array(db.get('relationships', relationship))
+    return relationship_vector
+
+llm.add_entity_vector_fn(get_entity_vector)
+llm.add_relationship_vector_fn(get_relationship_vector)
+
+# Test the system
+llm.process('Alice is friends with Bob and Charlie')
\ No newline at end of file