vv-llm 0.3.73__tar.gz

vv_llm-0.3.73/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Anderson
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

vv_llm-0.3.73/PKG-INFO

@@ -0,0 +1,174 @@
+Metadata-Version: 2.1
+Name: vv-llm
+Version: 0.3.73
+Summary: Universal LLM interfaces for multi-provider chat and utilities
+Author-Email: Anderson <andersonby@163.com>
+License: MIT
+Requires-Python: >=3.10
+Requires-Dist: openai>=1.99.3
+Requires-Dist: tiktoken>=0.7.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: anthropic>=0.47.1
+Requires-Dist: pydantic>=2.8.2
+Requires-Dist: Pillow>=10.4.0
+Requires-Dist: deepseek-tokenizer>=0.1.0
+Requires-Dist: qwen-tokenizer>=0.2.0
+Provides-Extra: bedrock
+Requires-Dist: boto3>=1.28.57; extra == "bedrock"
+Requires-Dist: botocore>=1.31.57; extra == "bedrock"
+Provides-Extra: diskcache
+Requires-Dist: diskcache; extra == "diskcache"
+Provides-Extra: redis
+Requires-Dist: redis; extra == "redis"
+Provides-Extra: server
+Requires-Dist: fastapi; extra == "server"
+Requires-Dist: uvicorn; extra == "server"
+Provides-Extra: vertex
+Requires-Dist: google-auth>=2.35.0; extra == "vertex"
+Description-Content-Type: text/markdown
+
+# vv-llm
+
+Universal LLM interface layer for Python. One API, 16 backends, sync & async.
+
+```
+pip install vv-llm
+```
+
+## Supported Backends
+
+OpenAI | Anthropic | DeepSeek | Gemini | Qwen | Groq | Mistral | Moonshot | MiniMax | Yi | ZhiPuAI | Baichuan | StepFun | xAI | Ernie | Local
+
+Also supports Azure OpenAI, Vertex AI, and AWS Bedrock deployments.
+
+## Quick Start
+
+### Configure
+
+```python
+from vv_llm.settings import settings
+
+settings.load({
+    "VERSION": "2",
+    "endpoints": [
+        {
+            "id": "openai-default",
+            "api_base": "https://api.openai.com/v1",
+            "api_key": "sk-...",
+        }
+    ],
+    "backends": {
+        "openai": {
+            "models": {
+                "gpt-4o": {
+                    "id": "gpt-4o",
+                    "endpoints": ["openai-default"],
+                }
+            }
+        }
+    }
+})
+```
+
+### Sync
+
+```python
+from vv_llm.chat_clients import create_chat_client, BackendType
+
+client = create_chat_client(BackendType.OpenAI, model="gpt-4o")
+resp = client.create_completion([
+    {"role": "user", "content": "Explain RAG in one sentence"}
+])
+print(resp.content)
+```
+
+### Streaming
+
+```python
+for chunk in client.create_stream([
+    {"role": "user", "content": "Write a haiku"}
+]):
+    if chunk.content:
+        print(chunk.content, end="")
+```
+
+### Async
+
+```python
+import asyncio
+from vv_llm.chat_clients import create_async_chat_client, BackendType
+
+async def main():
+    client = create_async_chat_client(BackendType.OpenAI, model="gpt-4o")
+    resp = await client.create_completion([
+        {"role": "user", "content": "hello"}
+    ])
+    print(resp.content)
+
+asyncio.run(main())
+```
+
+## Features
+
+- **Unified interface** — same `create_completion` / `create_stream` API across all providers
+- **Type-safe factory** — `create_chat_client(BackendType.X)` returns the correct client type
+- **Multi-endpoint** — configure multiple endpoints per backend with random selection and failover
+- **Tool calling** — normalized tool/function calling across providers
+- **Multimodal** — text + image inputs where supported
+- **Thinking/reasoning** — access chain-of-thought from Claude, DeepSeek Reasoner, etc.
+- **Token counting** — per-model tokenizers (tiktoken, deepseek-tokenizer, qwen-tokenizer)
+- **Rate limiting** — RPM/TPM controls with memory, Redis, or DiskCache backends
+- **Context length control** — automatic message truncation to fit model limits
+- **Prompt caching** — Anthropic prompt caching support
+- **Retry with backoff** — configurable retry logic for transient failures
+
+## Utilities
+
+```python
+from vv_llm.chat_clients import format_messages, get_token_counts, get_message_token_counts
+```
+
+| Function | Description |
+|---|---|
+| `format_messages` | Normalize multimodal/tool messages across formats |
+| `get_token_counts` | Count tokens for a text string |
+| `get_message_token_counts` | Count tokens for a message list |
+
+## Optional Dependencies
+
+```bash
+pip install 'vv-llm[redis]'      # Redis rate limiting
+pip install 'vv-llm[diskcache]'  # DiskCache rate limiting
+pip install 'vv-llm[server]'     # FastAPI token server
+pip install 'vv-llm[vertex]'     # Google Vertex AI
+pip install 'vv-llm[bedrock]'    # AWS Bedrock
+```
+
+## Project Structure
+
+```
+src/vv_llm/
+  chat_clients/    # Per-backend clients + factory
+  settings/        # Configuration management
+  types/           # Type definitions & enums
+  utilities/       # Rate limiting, retry, media processing, token counting
+  server/          # Optional token counting server
+
+tests/unit/        # Unit tests
+tests/live/        # Live integration tests (requires real API keys)
+```
+
+## Development
+
+```bash
+pdm install -d          # Install dev dependencies
+pdm run lint            # Ruff linter
+pdm run format-check    # Ruff format check
+pdm run type-check      # Ty type checker
+pdm run test            # Unit tests
+pdm run test-live       # Live tests (needs real endpoints)
+```
+
+## License
+
+MIT

vv_llm-0.3.73/README.md

@@ -0,0 +1,145 @@
+# vv-llm
+
+Universal LLM interface layer for Python. One API, 16 backends, sync & async.
+
+```
+pip install vv-llm
+```
+
+## Supported Backends
+
+OpenAI | Anthropic | DeepSeek | Gemini | Qwen | Groq | Mistral | Moonshot | MiniMax | Yi | ZhiPuAI | Baichuan | StepFun | xAI | Ernie | Local
+
+Also supports Azure OpenAI, Vertex AI, and AWS Bedrock deployments.
+
+## Quick Start
+
+### Configure
+
+```python
+from vv_llm.settings import settings
+
+settings.load({
+    "VERSION": "2",
+    "endpoints": [
+        {
+            "id": "openai-default",
+            "api_base": "https://api.openai.com/v1",
+            "api_key": "sk-...",
+        }
+    ],
+    "backends": {
+        "openai": {
+            "models": {
+                "gpt-4o": {
+                    "id": "gpt-4o",
+                    "endpoints": ["openai-default"],
+                }
+            }
+        }
+    }
+})
+```
+
+### Sync
+
+```python
+from vv_llm.chat_clients import create_chat_client, BackendType
+
+client = create_chat_client(BackendType.OpenAI, model="gpt-4o")
+resp = client.create_completion([
+    {"role": "user", "content": "Explain RAG in one sentence"}
+])
+print(resp.content)
+```
+
+### Streaming
+
+```python
+for chunk in client.create_stream([
+    {"role": "user", "content": "Write a haiku"}
+]):
+    if chunk.content:
+        print(chunk.content, end="")
+```
+
+### Async
+
+```python
+import asyncio
+from vv_llm.chat_clients import create_async_chat_client, BackendType
+
+async def main():
+    client = create_async_chat_client(BackendType.OpenAI, model="gpt-4o")
+    resp = await client.create_completion([
+        {"role": "user", "content": "hello"}
+    ])
+    print(resp.content)
+
+asyncio.run(main())
+```
+
+## Features
+
+- **Unified interface** — same `create_completion` / `create_stream` API across all providers
+- **Type-safe factory** — `create_chat_client(BackendType.X)` returns the correct client type
+- **Multi-endpoint** — configure multiple endpoints per backend with random selection and failover
+- **Tool calling** — normalized tool/function calling across providers
+- **Multimodal** — text + image inputs where supported
+- **Thinking/reasoning** — access chain-of-thought from Claude, DeepSeek Reasoner, etc.
+- **Token counting** — per-model tokenizers (tiktoken, deepseek-tokenizer, qwen-tokenizer)
+- **Rate limiting** — RPM/TPM controls with memory, Redis, or DiskCache backends
+- **Context length control** — automatic message truncation to fit model limits
+- **Prompt caching** — Anthropic prompt caching support
+- **Retry with backoff** — configurable retry logic for transient failures
+
+## Utilities
+
+```python
+from vv_llm.chat_clients import format_messages, get_token_counts, get_message_token_counts
+```
+
+| Function | Description |
+|---|---|
+| `format_messages` | Normalize multimodal/tool messages across formats |
+| `get_token_counts` | Count tokens for a text string |
+| `get_message_token_counts` | Count tokens for a message list |
+
+## Optional Dependencies
+
+```bash
+pip install 'vv-llm[redis]'      # Redis rate limiting
+pip install 'vv-llm[diskcache]'  # DiskCache rate limiting
+pip install 'vv-llm[server]'     # FastAPI token server
+pip install 'vv-llm[vertex]'     # Google Vertex AI
+pip install 'vv-llm[bedrock]'    # AWS Bedrock
+```
+
+## Project Structure
+
+```
+src/vv_llm/
+  chat_clients/    # Per-backend clients + factory
+  settings/        # Configuration management
+  types/           # Type definitions & enums
+  utilities/       # Rate limiting, retry, media processing, token counting
+  server/          # Optional token counting server
+
+tests/unit/        # Unit tests
+tests/live/        # Live integration tests (requires real API keys)
+```
+
+## Development
+
+```bash
+pdm install -d          # Install dev dependencies
+pdm run lint            # Ruff linter
+pdm run format-check    # Ruff format check
+pdm run type-check      # Ty type checker
+pdm run test            # Unit tests
+pdm run test-live       # Live tests (needs real endpoints)
+```
+
+## License
+
+MIT

vv_llm-0.3.73/pyproject.toml

@@ -0,0 +1,118 @@
+[project]
+authors = [
+    { name = "Anderson", email = "andersonby@163.com" },
+]
+dependencies = [
+    "openai>=1.99.3",
+    "tiktoken>=0.7.0",
+    "httpx>=0.27.0",
+    "anthropic>=0.47.1",
+    "pydantic>=2.8.2",
+    "Pillow>=10.4.0",
+    "deepseek-tokenizer>=0.1.0",
+    "qwen-tokenizer>=0.2.0",
+]
+description = "Universal LLM interfaces for multi-provider chat and utilities"
+name = "vv-llm"
+readme = "README.md"
+requires-python = ">=3.10"
+version = "0.3.73"
+
+[project.license]
+text = "MIT"
+
+[project.optional-dependencies]
+bedrock = [
+    "boto3 >= 1.28.57",
+    "botocore >= 1.31.57",
+]
+diskcache = [
+    "diskcache",
+]
+redis = [
+    "redis",
+]
+server = [
+    "fastapi",
+    "uvicorn",
+]
+vertex = [
+    "google-auth>=2.35.0",
+]
+
+[build-system]
+build-backend = "pdm.backend"
+requires = [
+    "pdm-backend",
+]
+
+[tool.pdm]
+distribution = true
+
+[tool.pdm.build]
+excludes = [
+    "tests",
+]
+
+[tool.pdm.scripts]
+format = "ruff format src/"
+format-check = "ruff format --check src/"
+lint = "ruff check src/"
+type-check = "ty check src/ --output-format concise --exit-zero"
+
+[tool.pdm.scripts.check-all]
+composite = [
+    "lint",
+    "format-check",
+    "type-check",
+]
+
+[tool.pdm.scripts.test]
+cmd = "pytest tests/unit"
+env_file = ".env"
+
+[tool.pdm.scripts.test-live]
+cmd = "python tests/live/run_live_tests.py"
+
+[tool.pdm.scripts.test-live.env]
+VV_LLM_RUN_LIVE_TESTS = "1"
+
+[tool.ruff]
+line-length = 180
+target-version = "py310"
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "I",
+    "B",
+    "C4",
+    "UP",
+]
+ignore = [
+    "E501",
+    "I001",
+]
+
+[tool.ruff.format]
+indent-style = "space"
+line-ending = "auto"
+quote-style = "double"
+
+[tool.pytest.ini_options]
+pythonpath = [
+    "tests",
+]
+testpaths = [
+    "tests/unit",
+]
+
+[dependency-groups]
+dev = [
+    "types-redis>=4.6.0.20241004",
+    "pytest>=8.3.4",
+    "ruff>=0.8.0",
+    "ty>=0.0.1a24",
+]

vv_llm-0.3.73/src/vv_llm/__init__.py

@@ -0,0 +1 @@
+