adding cli_config aand client changes

.github/workflows/docker-integration-tests.yaml

@@ -58,6 +58,7 @@ jobs:
         pipx install poetry==1.8.2
         poetry install -E dev
         poetry run pytest -s tests/test_client.py
+        poetry run pytest -s tests/test_concurrent_connections.py
 
     - name: Print docker logs if tests fail
       if: failure()

.github/workflows/rdme-openapi.yml

@@ -25,9 +25,9 @@ jobs:
       - name: "Setup Python, Poetry and Dependencies"
         uses: packetcoders/action-setup-cache-python-poetry@main
         with:
-          python-version: "3.11"
-          poetry-version: "1.7.1"
-          install-args: "--all-extras"
+          python-version: "3.12"
+          poetry-version: "1.8.2"
+          install-args: "-E dev"
 
       - name: Generate openapi.json file
         run: |

.github/workflows/test_local.yml

@@ -0,0 +1,28 @@
+name: Endpoint (Local)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: "Setup Python, Poetry and Dependencies"
+      uses: packetcoders/action-setup-cache-python-poetry@main
+      with:
+        python-version: "3.12"
+        poetry-version: "1.8.2"
+        install-args: "-E dev -E local"
+
+    - name: Test embedding endpoint
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_embedding_endpoint_local

.github/workflows/test_memgpt_hosted.yml

@@ -0,0 +1,30 @@
+name: Endpoint (MemGPT)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: "Setup Python, Poetry and Dependencies"
+      uses: packetcoders/action-setup-cache-python-poetry@main
+      with:
+        python-version: "3.12"
+        poetry-version: "1.8.2"
+        install-args: "-E dev"
+
+    - name: Test LLM endpoint
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_llm_endpoint_memgpt_hosted
+
+    - name: Test embedding endpoint
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_embedding_endpoint_memgpt_hosted

.github/workflows/test_ollama.yml

@@ -0,0 +1,38 @@
+name: Endpoint (Ollama)
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: Start Ollama Server
+      run: |
+        curl -fsSL https://ollama.com/install.sh | sh
+        ollama serve &
+        sleep 10 # wait for server
+        ollama pull dolphin2.2-mistral:7b-q6_K
+        ollama pull mxbai-embed-large
+
+    - name: "Setup Python, Poetry and Dependencies"
+      uses: packetcoders/action-setup-cache-python-poetry@main
+      with:
+        python-version: "3.12"
+        poetry-version: "1.8.2"
+        install-args: "-E dev -E ollama"
+
+    - name: Test LLM endpoint
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_llm_endpoint_ollama
+
+    - name: Test embedding endpoint
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_embedding_endpoint_ollama

.github/workflows/test_openai.yml

@@ -0,0 +1,43 @@
+name: Endpoint (OpenAI)
+
+env:
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: "Setup Python, Poetry and Dependencies"
+      uses: packetcoders/action-setup-cache-python-poetry@main
+      with:
+        python-version: "3.12"
+        poetry-version: "1.8.2"
+        install-args: "-E dev"
+
+    - name: Initialize credentials
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run memgpt quickstart --backend openai
+
+    - name: Test LLM endpoint
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_llm_endpoint_openai
+
+    - name: Test embedding endpoint
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      run: |
+        poetry run pytest -s -vv tests/test_endpoints.py::test_embedding_endpoint_openai

.github/workflows/tests.yml

@@ -2,7 +2,6 @@ name: Run All pytest Tests
 
 env:
   MEMGPT_PGURI: ${{ secrets.MEMGPT_PGURI }}
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
 
 on:
   push:
@@ -14,30 +13,29 @@ jobs:
   test:
     runs-on: ubuntu-latest
     timeout-minutes: 15
+
+    services:
+      qdrant:
+        image: qdrant/qdrant
+        ports:
+          - 6333:6333
+
     steps:
     - name: Checkout
       uses: actions/checkout@v4
 
     - name: Build and run container
       run: bash db/run_postgres.sh
 
-
     - name: "Setup Python, Poetry and Dependencies"
       uses: packetcoders/action-setup-cache-python-poetry@main
       with:
         python-version: "3.12"
         poetry-version: "1.8.2"
-        install-args: "--all-extras"
+        install-args: "-E dev -E postgres -E milvus"
 
     - name: Initialize credentials
-      env:
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-        if [ -z "$OPENAI_API_KEY" ]; then
-          poetry run memgpt quickstart --backend openai
-        else
-          poetry run memgpt quickstart --backend memgpt
-        fi
+      run: poetry run memgpt quickstart --backend memgpt
 
     #- name: Run docker compose server
     #  env:
@@ -56,7 +54,6 @@ jobs:
         MEMGPT_PG_PASSWORD: memgpt
         MEMGPT_PG_DB: memgpt
         MEMGPT_PG_HOST: localhost
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         MEMGPT_SERVER_PASS: test_server_token
       run: |
         poetry run pytest -s -vv tests/test_server.py
@@ -68,11 +65,10 @@ jobs:
         MEMGPT_PG_PASSWORD: memgpt
         MEMGPT_PG_HOST: localhost
         MEMGPT_PG_DB: memgpt
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         MEMGPT_SERVER_PASS: test_server_token
         PYTHONPATH: ${{ github.workspace }}:${{ env.PYTHONPATH }}
       run: |
-        poetry run pytest -s -vv -k "not test_storage and not test_server and not test_openai_client" tests
+        poetry run pytest -s -vv -k "not test_concurrent_connections.py and not test_quickstart and not test_endpoints and not test_storage and not test_server and not test_openai_client" tests
 
     - name: Run storage tests
       env:
@@ -81,7 +77,6 @@ jobs:
         MEMGPT_PG_PASSWORD: memgpt
         MEMGPT_PG_HOST: localhost
         MEMGPT_PG_DB: memgpt
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         MEMGPT_SERVER_PASS: test_server_token
       run: |
         poetry run pytest -s -vv tests/test_storage.py

.gitignore

@@ -1015,4 +1015,5 @@ pgdata/
 
 ## pytest mirrors
 memgpt/.pytest_cache/
-memgpy/pytest.ini
+memgpy/pytest.ini
+**/**/pytest_cache

Dockerfile

@@ -1,8 +1,8 @@
 # The builder image, used to build the virtual environment
-FROM python:3.11-bookworm as builder
+FROM python:3.12.2-bookworm as builder
 ARG MEMGPT_ENVIRONMENT=PRODUCTION
 ENV MEMGPT_ENVIRONMENT=${MEMGPT_ENVIRONMENT}
-RUN pip install poetry==1.4.2
+RUN pip install poetry==1.8.2
 
 ENV POETRY_NO_INTERACTION=1 \
     POETRY_VIRTUALENVS_IN_PROJECT=1 \
@@ -16,13 +16,13 @@ RUN poetry lock --no-update
 RUN if [ "$MEMGPT_ENVIRONMENT" = "DEVELOPMENT"  ] ; then \
     poetry install --no-root -E "postgres server dev autogen" ; \
     else \
-    poetry install --without dev --no-root -E "postgres server" && \
+    poetry install --no-root -E "postgres server" && \
     rm -rf $POETRY_CACHE_DIR ;  \
     fi
 
 
 # The runtime image, used to just run the code provided its virtual environment
-FROM python:3.11-slim-bookworm as runtime
+FROM python:3.12.2-slim-bookworm as runtime
 ARG MEMGPT_ENVIRONMENT=PRODUCTION
 ENV MEMGPT_ENVIRONMENT=${MEMGPT_ENVIRONMENT}
 ENV VIRTUAL_ENV=/app/.venv \

README.md

@@ -18,18 +18,18 @@ MemGPT makes it easy to build and deploy stateful LLM agents with support for:
 * Connections to [external data sources](https://memgpt.readme.io/docs/data_sources) (e.g. PDF files) for RAG
 * Defining and calling [custom tools](https://memgpt.readme.io/docs/functions) (e.g. [google search](https://github.com/cpacker/MemGPT/blob/main/examples/google_search.py))
 
-You can also use MemGPT to depoy agents as a *service*. You can use a MemGPT server to run a multi-user, multi-agent application on top of supported LLM providers.
+You can also use MemGPT to deploy agents as a *service*. You can use a MemGPT server to run a multi-user, multi-agent application on top of supported LLM providers.
 
 <img width="1000" alt="image" src="https://github.com/cpacker/MemGPT/assets/8505980/1096eb91-139a-4bc5-b908-fa585462da09">
 
 
-## Installation & Setup   
+## Installation & Setup
 Install MemGPT:
 ```sh
 pip install -U pymemgpt
 ```
 
-To use MemGPT with OpenAI, set the environment variable `OPENAI_API_KEY` to your OpenAI key then run: 
+To use MemGPT with OpenAI, set the environment variable `OPENAI_API_KEY` to your OpenAI key then run:
 ```
 memgpt quickstart --backend openai
 ```
@@ -54,19 +54,20 @@ MemGPT provides a developer portal that enables you to easily create, edit, moni
 
 <img width="1000" alt="image" src="https://github.com/cpacker/MemGPT/assets/5475622/071117c5-46a7-4953-bc9d-d74880e66258">
 
-## Quickstart (Server)  
+## Quickstart (Server)
 
-**Option 1 (Recommended)**: Run with docker compose  
+**Option 1 (Recommended)**: Run with docker compose
 1. [Install docker on your system](https://docs.docker.com/get-docker/)
 2. Clone the repo: `git clone https://github.com/cpacker/MemGPT.git`
-3. Run `docker compose up`
-4. Go to `memgpt.localhost` in the browser to view the developer portal 
+3. Copy-paste `.env.example` to `.env` and optionally modify
+4. Run `docker compose up`
+5. Go to `memgpt.localhost` in the browser to view the developer portal
 
 **Option 2:** Run with the CLI:
 1. Run `memgpt server`
 2. Go to `localhost:8283` in the browser to view the developer portal
 
-Once the server is running, you can use the [Python client](https://memgpt.readme.io/docs/admin-client) or [REST API](https://memgpt.readme.io/reference/api) to connect to `memgpt.localhost` (if you're running with docker compose) or `localhost:8283` (if you're running with the CLI) to create users, agents, and more. The service requires authentication with a MemGPT admin password, which can be set with running `export MEMGPT_SERVER_PASS=password`. 
+Once the server is running, you can use the [Python client](https://memgpt.readme.io/docs/admin-client) or [REST API](https://memgpt.readme.io/reference/api) to connect to `memgpt.localhost` (if you're running with docker compose) or `localhost:8283` (if you're running with the CLI) to create users, agents, and more. The service requires authentication with a MemGPT admin password; it is the value of `MEMGPT_SERVER_PASS` in `.env`.
 
 ## Supported Endpoints & Backends
 MemGPT is designed to be model and provider agnostic. The following LLM and embedding endpoints are supported:
@@ -80,7 +81,7 @@ MemGPT is designed to be model and provider agnostic. The following LLM and embe
 | Groq                | ✅ (alpha release) | ❌                  |
 | Cohere API          | ✅               | ❌                  |
 | vLLM                | ✅               | ❌                  |
-| Ollama              | ✅               | ❌                  |
+| Ollama              | ✅               | ✅                  |
 | LM Studio           | ✅               | ❌                  |
 | koboldcpp           | ✅               | ❌                  |
 | oobabooga web UI    | ✅               | ❌                  |
@@ -95,12 +96,11 @@ When using MemGPT with open LLMs (such as those downloaded from HuggingFace), th
 * **Report Issues or Suggest Features**: Have an issue or a feature request? Please submit them through our [GitHub Issues page](https://github.com/cpacker/MemGPT/issues).
 * **Explore the Roadmap**: Curious about future developments? View and comment on our [project roadmap](https://github.com/cpacker/MemGPT/issues/1200).
 * **Benchmark the Performance**: Want to benchmark the performance of a model on MemGPT? Follow our [Benchmarking Guidance](#benchmarking-guidance).
-* **Join Community Events**: Stay updated with the [MemGPT event calendar](https://lu.ma/berkeley-llm-meetup) or follow our [Twitter account](https://twitter.com/MemGPT). 
+* **Join Community Events**: Stay updated with the [MemGPT event calendar](https://lu.ma/berkeley-llm-meetup) or follow our [Twitter account](https://twitter.com/MemGPT).
 
 
 ## Benchmarking Guidance
 To evaluate the performance of a model on MemGPT, simply configure the appropriate model settings using `memgpt configure`, and then initiate the benchmark via `memgpt benchmark`. The duration will vary depending on your hardware. This will run through a predefined set of prompts through multiple iterations to test the function calling capabilities of a model. You can help track what LLMs work well with MemGPT by contributing your benchmark results via [this form](https://forms.gle/XiBGKEEPFFLNSR348), which will be used to update the spreadsheet.
 
 ## Legal notices
 By using MemGPT and related MemGPT services (such as the MemGPT endpoint or hosted service), you agree to our [privacy policy](https://github.com/cpacker/MemGPT/tree/main/PRIVACY.md) and [terms of service](https://github.com/cpacker/MemGPT/tree/main/TERMS.md).
-

configs/embedding_model_configs/local.json

@@ -0,0 +1,7 @@
+{
+    "embedding_endpoint": null,
+    "embedding_model": "BAAI/bge-small-en-v1.5",
+    "embedding_dim": 384,
+    "embedding_chunk_size": 300,
+    "embedding_endpoint_type": "local"
+}

configs/embedding_model_configs/memgpt-hosted.json

@@ -2,5 +2,6 @@
     "embedding_endpoint": "https://embeddings.memgpt.ai",
     "embedding_model": "BAAI/bge-large-en-v1.5",
     "embedding_dim": 1024,
-    "embedding_chunk_size": 300
+    "embedding_chunk_size": 300,
+    "embedding_endpoint_type": "hugging-face"
 }

configs/embedding_model_configs/ollama.json

@@ -0,0 +1,7 @@
+{
+    "embedding_endpoint_type": "ollama",
+    "embedding_endpoint": "http://127.0.0.1:11434",
+    "embedding_model": "mxbai-embed-large",
+    "embedding_dim": 512,
+    "embedding_chunk_size": 200
+}

configs/llm_model_configs/ollama.json

@@ -0,0 +1,6 @@
+{
+    "context_window": 8192,
+    "model_endpoint_type": "ollama",
+    "model_endpoint": "http://127.0.0.1:11434",
+    "model": "dolphin2.2-mistral:7b-q6_K"
+}

dev-compose.yaml

@@ -22,6 +22,7 @@ services:
     build:
       context: .
       dockerfile: Dockerfile
+      target: runtime
     depends_on:
       - memgpt_db
     ports:
@@ -35,6 +36,7 @@ services:
       - MEMGPT_PG_HOST=pgvector_db
       - MEMGPT_PG_PORT=5432
       - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - SERPAPI_API_KEY=${SERPAPI_API_KEY}
     volumes:
       - ./configs/server_config.yaml:/root/.memgpt/config # config file
       # ~/.memgpt/credentials:/root/.memgpt/credentials # credentials file