Python client (kernel-memory-client, kernel-memory-cli, semantic-kernel-memory-plugin)

clients/python/README.md

@@ -0,0 +1,90 @@
+# Microsoft Kernel Memory Python Libraries 🐍
+
+This directory contains three Python packages that provide different ways to interact with Microsoft Kernel Memory:
+
+## 📦 kernel-memory-client
+
+An autogenerated Python client library for interacting with the Kernel Memory API. This client provides low-level access to all Kernel Memory endpoints and operations.
+
+```python
+from kernel_memory_client import Client
+
+# Create a client
+client = Client(base_url="http://localhost:9001")
+
+# Use the client to interact with Kernel Memory
+# ...
+```
+
+**Generation Info:** The client was autogenerated using the OpenAPI specification (`swagger.json`) and the `openapi-python-client` tool:
+
+```shell
+cd clients/python/kernel-memory-cli
+openapi-python-client generate --path ../../swagger.json --config openapi-python-generator-config.yml --overwrrite
+```
+
+**Note:** The following patch was applied to fix the document upload functionality:
+
+```patch
+# clients/python/kernel-memory-client/kernel_memory_client/models/upload_document_body.py
+@@ -1,11 +1,3 @@
+         files: Union[Unset, tuple[None, bytes, str]] = UNSET
+         if not isinstance(self.files, Unset):
+-            _temp_files = []
+-            for files_item_data in self.files:
+-                files_item = files_item_data.to_tuple()
+-
+-                _temp_files.append(files_item)
+-            files = (None, json.dumps(_temp_files).encode(), "application/json")
+-            
++            files = files
+```
+
+## 🖥️ kernel-memory-cli
+
+A command-line interface for Microsoft Kernel Memory that provides an easy way to interact with Kernel Memory services from the terminal.
+
+```bash
+# Install the CLI
+pip install kernel-memory-cli
+
+# Configure the CLI
+kernel-memory config --base-url http://localhost:9001
+
+# Upload a document
+kernel-memory upload mydocument.pdf
+
+# Search for information
+kernel-memory search "my query"
+
+# Ask questions about your documents
+kernel-memory ask "What does my document say about machine learning?"
+```
+
+The CLI offers intuitive commands for configuring connections, uploading documents, searching content, and asking questions about your indexed documents.
+
+## 🔌 semantic-kernel-memory-plugin
+
+A plugin that integrates Kernel Memory with Semantic Kernel, allowing you to use Kernel Memory's document processing and retrieval capabilities within your Semantic Kernel applications.
+
+```python
+from semantic_kernel import Kernel
+from semantic_kernel_memory_plugin.memory_plugin import MemoryPlugin
+from kernel_memory_client import Client, AuthenticatedClient
+
+# Create a Semantic Kernel instance
+kernel = Kernel()
+
+# Add the Kernel Memory plugin
+
+memory_client = AuthenticatedClient(
+        base_url="http://localhost:9001")
+
+memory_plugin = MemoryPlugin(memory_client=memory_client)
+kernel.add_plugin(memory_plugin)
+
+# Now use Kernel Memory capabilities in your Semantic Kernel app
+# ...
+```
+
+This plugin bridges the powerful memory capabilities of Kernel Memory with the flexible AI orchestration of Semantic Kernel.

clients/python/kernel-memory-cli/README.md

@@ -0,0 +1,128 @@
+# Kernel Memory CLI
+
+A command line interface for Microsoft Kernel Memory based on python.
+
+## Installation
+
+```bash
+pip install kernel-memory-cli
+```
+
+## Getting Started
+
+Before using Kernel Memory CLI, you need to configure it:
+
+```bash
+kernel-memory config --base-url http://localhost:9001
+```
+
+If you need authentication:
+
+```bash
+kernel-memory config --base-url http://your-api-url --token your-api-token
+```
+
+## Commands
+
+### Configuration
+
+- Set up the CLI:
+    ```bash
+    kernel-memory config --base-url <url> [--token <token>] [--default-index <index>]
+    ```
+
+- View current configuration:
+    ```bash
+    kernel-memory show
+    ```
+
+### Working with Documents
+
+- Upload a document:
+    ```bash
+    kernel-memory upload <file_path> [--index <index>] [--document-id <id>] [--tags <tag1:value1>]
+    ```
+
+- Search document snippets:
+    ```bash
+    kernel-memory search "your search query" [--index <index>] [--limit 3] [--filter-tags <tag1:value1>]
+    ```
+
+- Ask questions:
+    ```bash
+    kernel-memory ask "your question" [--index <index>] [--filter-tags <tag1:value1>]
+    ```
+
+- List available indices:
+    ```bash
+    kernel-memory list
+    ```
+
+![Help](./docs/help.png)
+![List](./docs/list.png)
+
+## Advanced Usage Examples
+
+### Custom Processing Pipeline
+
+You can customize the document processing pipeline using the `--steps` option when uploading:
+
+```bash
+kernel-memory upload --steps extract --steps partition --steps gen_embeddings --steps save_records mydocs-NASA-news.pdf
+```
+
+This command uploads a PDF document about NASA news and processes it through these specific pipeline steps:
+1. `extract` - Extracts text content from the PDF
+2. `partition` - Divides the content into manageable chunks
+3. `gen_embeddings` - Generates vector embeddings for each chunk
+4. `save_records` - Saves the processed chunks in the index
+
+![Upload](./docs/upload.png)
+
+### Searching for Information
+
+To search for specific information in your documents:
+
+```bash
+kernel-memory search "Tell me the latest news about Artemis (a Nasa project)"
+```
+
+This command performs a semantic search in your index and returns the most relevant document snippets related to the Artemis project. Each result shows:
+- Document ID
+- Relevant content snippet
+- Relevance score
+- Associated tags (if available)
+
+![Search](./docs/search.png)
+
+### Asking Questions
+
+For more advanced question answering:
+
+```bash
+kernel-memory ask "Tell me the latest news about Artemis (a Nasa project)"
+```
+
+Unlike the search command that returns raw snippets, the `ask` command:
+1. Retrieves the most relevant information about the Artemis project
+2. Generates a comprehensive answer synthesizing the information
+3. Provides citations to the source documents
+4. Creates a cohesive response that directly answers your question
+
+![Ask](./docs/ask.png)
+
+## Environment Variables
+
+You can configure the CLI using environment variables:
+
+- `KM_BASE_URL` - Base URL for the API
+- `KM_TOKEN` - Authentication token
+- `KM_TOKEN_PREFIX` - Prefix for the token
+- `KM_DEFAULT_INDEX` - Default index to use
+- `KM_TIMEOUT` - Request timeout in seconds
+- `KM_VERIFY_SSL` - Whether to verify SSL certificates
+- `KM_CONFIG_PATH` - Path to config file
+
+## License
+
+[MIT License](LICENSE)