132/llama3.2+nomic

.dockerignore

@@ -0,0 +1,7 @@
+.venv
+.env.local
+.env.sample
+.gitignore
+.pre-commit-config.yaml
+.github
+.idea

Makefile

@@ -28,20 +28,22 @@ lint:
 format:
 	black --config pyproject.toml labs
 
-## Teardown local database
+## Stops and removes all the services
 .PHONY: down
 down:
 	docker compose --env-file=$(ENV_FILE) down
 
-## Setup local database
+## Start all the services
 .PHONY: up
 up: down
 	docker compose --env-file=$(ENV_FILE) up --build -d
 
+## Start a python shell
 .PHONY: shell
 shell:
 	ipython
 
+## Run project tests
 .PHONY: tests
 tests:
 	pytest
@@ -54,13 +56,11 @@ clean_tests:
 		rm -rf labs/test/vcr_cassettes; \
 	fi
 
-.PHONY: local_llm_up
-local_llm_up:
-	docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
+## Pull given model from ollama (use `make ollama model=<model name>`)
+.PHONY: ollama
+ollama:
+	docker compose exec ollama ollama pull $(model)
 
-.PHONY: local_llm_run
-local_llm_run: local_llm_up
-	docker exec ollama ollama run llama3.2
 
 #################################################################################
 # Self Documenting Commands                                                     #

asgi_app.py

@@ -20,6 +20,7 @@
 fastapi_app.include_router(codemonkey_endpoints.router)
 fastapi_app.include_router(github_endpoints.router)
 
+
 # ASGI application to route to Django or FastAPI
 async def app(scope, receive, send):
     if scope["type"] == "http" and scope["path"].startswith("/admin"):

config/admin.py

@@ -1,7 +1,8 @@
 from django.contrib import admin
 from .models import Config
 
+
 @admin.register(Config)
 class ConfigAdmin(admin.ModelAdmin):
-    list_display = ('llm_model', 'key', 'value', 'type', 'created_at', 'updated_at')
-    search_fields = (['key', 'llm_model'])
+    list_display = ("llm_model", "key", "value", "type", "created_at", "updated_at")
+    search_fields = ["key", "llm_model"]

config/configuration_variables.py

@@ -3,7 +3,6 @@
 
 from labs.logger import setup_logger
 
-
 setup_logger()
 
 
@@ -52,4 +51,4 @@
 REDIS_PORT = os.environ.get("REDIS_PORT")
 
 LOCAL_LLM = eval(os.environ.get("LOCAL_LLM", "False"))
-LOCAL_LLM_HOST = os.environ.get("LOCAL_LLM_HOST", "http://localhost:11434")
+LOCAL_LLM_HOST = os.environ.get("LOCAL_LLM_HOST", "http://ollama:11434")

config/migrations/0001_initial.py

@@ -5,7 +5,6 @@
 
 
 class Migration(migrations.Migration):
-
     initial = True
 
     dependencies = []

config/models/config.py

@@ -1,8 +1,9 @@
 from django.db import models
 from django.utils import timezone
 
+
 class Config(models.Model):
-    llm_model = models.TextField(blank=True, null=True) 
+    llm_model = models.TextField(blank=True, null=True)
     key = models.TextField(unique=True)
     value = models.TextField(blank=True, null=True)
     type = models.TextField(blank=True, null=True)
@@ -13,6 +14,4 @@ def __str__(self):
         return f"{self.key}: {self.value}"
 
     class Meta:
-        indexes = [
-            models.Index(fields=['key', 'llm_model'])
-        ]
+        indexes = [models.Index(fields=["key", "llm_model"])]

config/settings.py

@@ -9,6 +9,7 @@
 For the full list of settings and their values, see
 https://docs.djangoproject.com/en/5.1/ref/settings/
 """
+
 import os
 from pathlib import Path
 
@@ -19,12 +20,12 @@
 # See https://docs.djangoproject.com/en/5.1/howto/deployment/checklist/
 
 # SECURITY WARNING: keep the secret key used in production secret!
-SECRET_KEY = os.environ.get('DJANGO_SECRET_KEY', '')
+SECRET_KEY = os.environ.get("DJANGO_SECRET_KEY", "")
 
 # SECURITY WARNING: don't run with debug turned on in production!
-DEBUG = os.environ.get('DJANGO_DEBUG', "True") == "True"
+DEBUG = os.environ.get("DJANGO_DEBUG", "True") == "True"
 
-ALLOWED_HOSTS = [s.strip() for s in os.environ.get("DJANGO_ALLOWED_HOSTS", []).split(",")] 
+ALLOWED_HOSTS = [s.strip() for s in os.environ.get("DJANGO_ALLOWED_HOSTS", []).split(",")]
 
 
 # Application definition

config/urls.py

@@ -14,6 +14,7 @@
     1. Import the include() function: from django.urls import include, path
     2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
 """
+
 from django.contrib import admin
 from django.urls import path
 

database_scripts/postgres.sql

@@ -6,7 +6,7 @@ CREATE TABLE IF NOT EXISTS embeddings (
 id SERIAL PRIMARY KEY,
 repository text,
 embedding vector,
-file_and_path text,
+file_path text,
 text text,
 created_at timestamptz DEFAULT now()
 );

database_scripts/test.sql

@@ -6,7 +6,7 @@ CREATE TABLE IF NOT EXISTS embeddings (
 id SERIAL PRIMARY KEY,
 repository text,
 embedding vector,
-file_and_path text,
+file_path text,
 text text,
 created_at timestamptz DEFAULT now()
 );

docker-compose.yml

@@ -1,12 +1,4 @@
 services:
-  postgres:
-    container_name: postgres
-    image: postgres:13
-    environment:
-      POSTGRES_USER: ${DATABASE_USER}
-      POSTGRES_PASSWORD: ${DATABASE_PASS}
-      POSTGRES_DB: ${POSTGRES_DB}
-
   labs-db:
     container_name: labs-db
     image: pgvector/pgvector:pg16
@@ -70,4 +62,14 @@ services:
       - labs-db
     volumes:
       - .:/app
-      - ${LOCAL_REPOS_PATH}:/local-repos/
+      - ${LOCAL_REPOS_PATH}:/local-repos/
+
+  ollama:
+    image: ollama/ollama:latest
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama:/root/.ollama
+
+volumes:
+  ollama:

docs/diagram/class_diagram_script.py

@@ -1,5 +1,6 @@
-import os
 import ast
+import os
+
 import graphviz
 
 
@@ -28,9 +29,7 @@ def extract_classes(file_path):
                             args.append(f"{arg.arg}: {arg.annotation.id}")
                         elif isinstance(arg.annotation, ast.Subscript):
                             if isinstance(arg.annotation.value, ast.Name):
-                                args.append(
-                                    f"{arg.arg}: {arg.annotation.value.id}[{arg.annotation.slice.value.id}]"
-                                )
+                                args.append(f"{arg.arg}: {arg.annotation.value.id}[{arg.annotation.slice.value.id}]")
                         else:
                             args.append(arg.arg)
                     method_signature = f"{visibility} {method_name}({', '.join(args)})"

labs/celery.py

@@ -14,9 +14,7 @@
 LOW_PRIORITY_QUEUE_NAME = f"{CELERY_QUEUE_PREFIX}-low"
 HIGH_PRIORITY_QUEUE_NAME = f"{CELERY_QUEUE_PREFIX}-high"
 
-redis_client = redis.StrictRedis(
-    host=settings.REDIS_HOST, port=settings.REDIS_PORT, db=0, decode_responses=True
-)
+redis_client = redis.StrictRedis(host=settings.REDIS_HOST, port=settings.REDIS_PORT, db=0, decode_responses=True)
 
 
 app = Celery(

labs/database/connect.py

@@ -1,8 +1,9 @@
-from config import configuration_variables as settings
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker, declarative_base
 import logging
 
+from sqlalchemy import create_engine
+from sqlalchemy.orm import declarative_base, sessionmaker
+
+from config import configuration_variables as settings
 
 logger = logging.getLogger(__name__)
 
@@ -14,16 +15,16 @@
 
 def db_connector():
     def decorator(original_function):
-        def new_function(*args, **kwargs):
+        def new_function(self, *args, **kwargs):
             if settings.TEST_ENVIRONMENT:
                 # This is necessary because when we're running tests, we are already using db_session.
                 # Which has the rollback feature.
-                return original_function(*args, **kwargs)
+                return original_function(self, *args, **kwargs)
 
             connection = engine.connect()
 
             try:
-                return original_function(connection, *args, **kwargs)
+                return original_function(self, connection, *args, **kwargs)
             except Exception:
                 logger.exception("Error while getting data from DB.")
             finally:

labs/database/models.py

@@ -0,0 +1,17 @@
+import logging
+
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import Column, Integer, String
+
+from labs.database.connect import Base
+
+logger = logging.getLogger(__name__)
+
+
+class EmbeddingModel(Base):
+    __tablename__ = "embeddings"
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    repository = Column(String)
+    file_path = Column(String)
+    text = Column(String)
+    embedding = Column(Vector())