datasette-llm 0.1a0__tar.gz

datasette_llm-0.1a0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

datasette_llm-0.1a0/PKG-INFO

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: datasette-llm
+Version: 0.1a0
+Summary: LLM integration for Datasette
+Author: Simon Willison
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/datasette/datasette-llm
+Project-URL: Changelog, https://github.com/datasette/datasette-llm/releases
+Project-URL: Issues, https://github.com/datasette/datasette-llm/issues
+Project-URL: CI, https://github.com/datasette/datasette-llm/actions
+Classifier: Framework :: Datasette
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: datasette>=1.0a23
+Requires-Dist: llm>=0.26a0
+Requires-Dist: datasette-secrets
+Dynamic: license-file
+
+# datasette-llm
+
+[![PyPI](https://img.shields.io/pypi/v/datasette-llm.svg)](https://pypi.org/project/datasette-llm/)
+[![Changelog](https://img.shields.io/github/v/release/datasette/datasette-llm?include_prereleases&label=changelog)](https://github.com/datasette/datasette-llm/releases)
+[![Tests](https://github.com/datasette/datasette-llm/actions/workflows/test.yml/badge.svg)](https://github.com/datasette/datasette-llm/actions/workflows/test.yml)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/datasette/datasette-llm/blob/main/LICENSE)
+
+LLM integration for Datasette plugins.
+
+This plugin provides a standard interface for Datasette plugins to use LLM models via the [llm](https://llm.datasette.io/) library, with:
+
+- **Model management**: Control which models are available, with filtering and defaults
+- **API key management**: Integration with [datasette-secrets](https://github.com/datasette/datasette-secrets) for secure key storage
+- **Hooks for extensibility**: Track usage, enforce policies, implement accounting
+
+## Installation
+
+Install this plugin in the same environment as Datasette:
+
+```bash
+datasette install datasette-llm
+```
+
+You'll also need at least one LLM model plugin installed:
+
+```bash
+# For OpenAI models
+datasette install llm
+
+# For Anthropic models
+datasette install llm-anthropic
+
+# For testing without API calls
+datasette install llm-echo
+```
+
+## Configuration
+
+Configure the plugin in your `datasette.yaml`:
+
+```yaml
+plugins:
+  datasette-llm:
+    # Default model when none specified
+    default_model: gpt-4o-mini
+
+    # Purpose-specific model defaults
+    purposes:
+      enrichments:
+        model: gpt-4o-mini      # Cheap for bulk operations
+      sql-assistant:
+        model: gpt-4o           # Smarter for complex queries
+      chat:
+        model: claude-3-5-sonnet
+
+    # Model availability (optional)
+    models:                      # Allowlist - only these models available
+      - gpt-4o-mini
+      - gpt-4o
+      - claude-3-5-sonnet
+
+    # Or use a blocklist instead
+    blocked_models:
+      - o1-preview              # Too expensive
+
+    # Only show models with API keys configured (default: true)
+    require_keys: true
+```
+
+## API Key Management
+
+datasette-llm integrates with [datasette-secrets](https://github.com/datasette/datasette-secrets) for API key management. Keys are automatically registered for all installed model providers.
+
+### Setting up keys
+
+1. **Via environment variables** (recommended for deployment):
+   ```bash
+   export DATASETTE_SECRETS_OPENAI_API_KEY=sk-...
+   export DATASETTE_SECRETS_ANTHROPIC_API_KEY=sk-ant-...
+   ```
+
+2. **Via the web interface**: Navigate to `/-/secrets` (requires `manage-secrets` permission)
+
+3. **Via llm CLI** (fallback): Keys set with `llm keys set openai` are also used
+
+### Key resolution order
+
+1. datasette-secrets (env var `DATASETTE_SECRETS_<PROVIDER>_API_KEY` or encrypted database)
+2. llm's keys.json (`~/.config/io.datasette.llm/keys.json`)
+3. llm's environment variables (e.g., `OPENAI_API_KEY`)
+
+## Usage
+
+### Basic usage
+
+```python
+from datasette_llm import LLM
+
+async def my_plugin_view(datasette, request):
+    llm = LLM(datasette)
+
+    # Get a model (uses default if configured)
+    model = await llm.model()
+
+    # Or specify a model explicitly
+    model = await llm.model("gpt-4o-mini")
+
+    # Execute a prompt
+    response = await model.prompt("What is the capital of France?")
+    text = await response.text()
+```
+
+### The `purpose` parameter
+
+Specify a `purpose` to:
+- Select the right default model for the task
+- Enable purpose-based auditing and permissions
+- Allow purpose-specific budget limits (via datasette-llm-accountant)
+
+```python
+# Uses the model configured for "sql-assistant" purpose
+model = await llm.model(purpose="sql-assistant")
+
+# Or with explicit model (purpose still tracked)
+model = await llm.model("gpt-4o", purpose="sql-assistant")
+```
+
+### Streaming responses
+
+```python
+model = await llm.model("gpt-4o-mini")
+response = await model.prompt("Tell me a story")
+
+# Non-streaming - wait for complete response
+text = await response.text()
+
+# Streaming - process chunks as they arrive
+async for chunk in response:
+    print(chunk, end="", flush=True)
+```
+
+### Grouping prompts
+
+Use `group()` for batch operations where multiple prompts are logically related:
+
+```python
+async def enrich_rows(datasette, rows):
+    llm = LLM(datasette)
+
+    # Model determined by purpose configuration
+    async with llm.group(purpose="enrichments") as model:
+        results = []
+        for row in rows:
+            response = await model.prompt(f"Summarize: {row['content']}")
+            text = await response.text()
+            results.append(text)
+
+    # All responses guaranteed complete here
+    return results
+```
+
+Benefits of `group()`:
+- **Transactional semantics**: All responses forced to complete on exit
+- **Shared context**: Hooks can treat grouped prompts together (e.g., shared budget reservation)
+- **Cleanup**: The `llm_group_exit` hook is called for settlement/logging
+
+### Listing available models
+
+```python
+llm = LLM(datasette)
+
+# Get all available models (filtered by config and key availability)
+models = await llm.models()
+for model in models:
+    print(model.model_id)
+
+# Filter by actor (for per-user permissions)
+models = await llm.models(actor=request.actor)
+
+# Filter by purpose
+models = await llm.models(purpose="enrichments")
+```
+
+## Plugin Hooks
+
+datasette-llm provides hooks for other plugins to extend LLM operations.
+
+### `llm_prompt_context`
+
+Wrap prompt execution with custom logic:
+
+```python
+from datasette import hookimpl
+from contextlib import asynccontextmanager
+
+@hookimpl
+def llm_prompt_context(datasette, model_id, prompt, purpose):
+    @asynccontextmanager
+    async def wrapper(result):
+        # Before the prompt executes
+        print(f"Starting prompt to {model_id}")
+
+        yield
+
+        # After prompt() returns (response may still be streaming)
+        async def on_complete(response):
+            usage = await response.usage()
+            print(f"Used {usage.input} input, {usage.output} output tokens")
+
+        if result.response:
+            await result.response.on_done(on_complete)
+
+    return wrapper
+```
+
+### `llm_group_exit`
+
+Called when a `group()` context manager exits:
+
+```python
+@hookimpl
+def llm_group_exit(datasette, group):
+    # Can return a coroutine for async cleanup
+    async def cleanup():
+        print(f"Group for {group.purpose} completed")
+        print(f"Processed {len(group._responses)} prompts")
+    return cleanup()
+```
+
+### `llm_filter_models`
+
+Filter the list of available models:
+
+```python
+@hookimpl
+async def llm_filter_models(datasette, models, actor, purpose):
+    if not actor:
+        # Anonymous users get limited models
+        return [m for m in models if m.model_id == "gpt-4o-mini"]
+
+    # Check database for user's allowed models
+    db = datasette.get_database()
+    result = await db.execute(
+        "SELECT model_id FROM user_models WHERE user_id = ?",
+        [actor["id"]]
+    )
+    allowed = {row["model_id"] for row in result.rows}
+    return [m for m in models if m.model_id in allowed]
+```
+
+### `llm_default_model`
+
+Provide dynamic default model selection:
+
+```python
+@hookimpl
+async def llm_default_model(datasette, purpose, actor):
+    if actor:
+        # Check user's preferred model
+        db = datasette.get_database()
+        result = await db.execute(
+            "SELECT preferred_model FROM user_prefs WHERE user_id = ?",
+            [actor["id"]]
+        )
+        row = result.first()
+        if row:
+            return row["preferred_model"]
+    return None  # Use config defaults
+```
+
+## Related Plugins
+
+- **[datasette-secrets](https://github.com/datasette/datasette-secrets)**: Secure API key storage (required dependency)
+- **[datasette-llm-accountant](https://github.com/datasette/datasette-llm-accountant)**: Budget management and cost tracking
+
+## Development
+
+To set up this plugin locally:
+
+```bash
+cd datasette-llm
+uv sync
+
+# Confirm the plugin is visible
+uv run datasette plugins
+```
+
+To run the tests:
+
+```bash
+uv run pytest
+```
+
+The test suite uses the `llm-echo` model which echoes back prompts without making API calls.