Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

[Feat]: Add support for running chromadb in server mode with embedchain (#220)

Deshraj Yadav73dd7151cb39
diff --git a/Makefile b/Makefile
index b9e1dbe03..f0a500900 100644
--- a/Makefile
+++ b/Makefile
@@ -8,7 +8,7 @@ PROJECT_NAME := embedchain
install:
$(PIP) install --upgrade pip
- $(PIP) install .[dev]
+ $(PIP) install -e .[dev]
format:
$(PYTHON) -m black .
diff --git a/embedchain/config/InitConfig.py b/embedchain/config/InitConfig.py
index 90b562d3f..f06149564 100644
--- a/embedchain/config/InitConfig.py
+++ b/embedchain/config/InitConfig.py
@@ -9,7 +9,7 @@ class InitConfig(BaseConfig):
Config to initialize an embedchain `App` instance.
"""
- def __init__(self, log_level=None, ef=None, db=None):
+ def __init__(self, log_level=None, ef=None, db=None, host=None, port=None):
"""
:param log_level: Optional. (String) Debug level
['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
@@ -33,7 +33,7 @@ class InitConfig(BaseConfig):
if db is None:
from embedchain.vectordb.chroma_db import ChromaDB
- self.db = ChromaDB(ef=self.ef)
+ self.db = ChromaDB(ef=self.ef, host=host, port=port)
else:
self.db = db
diff --git a/embedchain/vectordb/chroma_db.py b/embedchain/vectordb/chroma_db.py
index de4887e15..40fc6b644 100644
--- a/embedchain/vectordb/chroma_db.py
+++ b/embedchain/vectordb/chroma_db.py
@@ -9,7 +9,7 @@ from embedchain.vectordb.base_vector_db import BaseVectorDB
class ChromaDB(BaseVectorDB):
"""Vector database using ChromaDB."""
- def __init__(self, db_dir=None, ef=None):
+ def __init__(self, db_dir=None, ef=None, host=None, port=None):
if ef:
self.ef = ef
else:
@@ -18,13 +18,21 @@ class ChromaDB(BaseVectorDB):
organization_id=os.getenv("OPENAI_ORGANIZATION"),
model_name="text-embedding-ada-002",
)
- if db_dir is None:
- db_dir = "db"
- self.client_settings = chromadb.config.Settings(
- chroma_db_impl="duckdb+parquet",
- persist_directory=db_dir,
- anonymized_telemetry=False,
- )
+
+ if host and port:
+ self.client_settings = chromadb.config.Settings(
+ chroma_api_impl="rest",
+ chroma_server_host=host,
+ chroma_server_http_port=port,
+ )
+ else:
+ if db_dir is None:
+ db_dir = "db"
+ self.client_settings = chromadb.config.Settings(
+ chroma_db_impl="duckdb+parquet",
+ persist_directory=db_dir,
+ anonymized_telemetry=False,
+ )
super().__init__()
def _get_or_create_db(self):
diff --git a/notebooks/embedchain-chromadb-server.ipynb b/notebooks/embedchain-chromadb-server.ipynb
new file mode 100644
index 000000000..a5adde38d
--- /dev/null
+++ b/notebooks/embedchain-chromadb-server.ipynb
@@ -0,0 +1,111 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "553f2e71",
+ "metadata": {},
+ "source": [
+ "## Embedchain chromadb server example"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "513e12e6",
+ "metadata": {},
+ "source": [
+ "This notebook shows an example of how you can use embedchain with chromdb (server). \n",
+ "\n",
+ "\n",
+ "First, run chroma inside docker using the following command:\n",
+ "\n",
+ "\n",
+ "```bash\n",
+ "git clone https://github.com/chroma-core/chroma\n",
+ "cd chroma && docker-compose up -d --build\n",
+ "```"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "92e7ad71",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "from embedchain.config import InitConfig\n",
+ "\n",
+ "\n",
+ "chromadb_host = \"localhost\"\n",
+ "chromadb_port = 8000\n",
+ "\n",
+ "config = InitConfig(host=chromadb_host, port=chromadb_port)\n",
+ "elon_bot = App(config)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "1a6d6841",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "All data from https://en.wikipedia.org/wiki/Elon_Musk already exists in the database.\n",
+ "All data from https://www.tesla.com/elon-musk already exists in the database.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Embed Online Resources\n",
+ "elon_bot.add(\"web_page\", \"https://en.wikipedia.org/wiki/Elon_Musk\")\n",
+ "elon_bot.add(\"web_page\", \"https://www.tesla.com/elon-musk\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "34cda99c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'Elon Musk runs four companies: Tesla, SpaceX, Neuralink, and The Boring Company.'"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "elon_bot.query(\"How many companies does Elon Musk run?\")"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.8.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}