adaptive-memory-multi-model-router 2.15.5 → 2.16.1

package/packages/a3m-vercel-ai/dist/index.js

@@ -1,79 +0,0 @@
-/**
- * @a3m/vercel-ai - A3M Router Provider for Vercel AI SDK
- *
- * Drop-in replacement that routes to the cheapest capable provider
- * with parallel execution, caching, and automatic fallback.
- *
- * @example
- * ```typescript
- * import { createA3MProvider } from '@a3m/vercel-ai';
- * import { generateText } from 'ai';
- *
- * const a3m = createA3MProvider();
- *
- * const { text } = await generateText({
- *   model: a3m('auto'),
- *   prompt: 'What is the capital of France?',
- * });
- * ```
- */
-export { createA3MLanguageModel } from './a3m-language-model';
-import { createA3MLanguageModel } from './a3m-language-model';
-/**
- * Create an A3M Router provider for Vercel AI SDK
- */
-export function createA3MProvider(config = {}) {
-    const languageModel = createA3MLanguageModel(config);
-    const provider = Object.assign((modelId) => {
-        // Return the language model - A3M handles model selection internally
-        return languageModel;
-    }, {
-        name: 'a3m',
-        // Allow accessing config for introspection
-        __config: config,
-    });
-    return provider;
-}
-/**
- * Example usage with Next.js App Router
- *
- * ```typescript
- * // app/api/chat/route.ts
- * import { createA3MProvider } from '@a3m/vercel-ai';
- * import { generateText } from 'ai';
- *
- * const a3m = createA3MProvider({
- *   parallelEnsemble: true,
- * });
- *
- * export async function POST(req: Request) {
- *   const { messages } = await req.json();
- *
- *   const result = await generateText({
- *     model: a3m('auto'),
- *     messages,
- *   });
- *
- *   return Response.json(result);
- * }
- * ```
- */
-/**
- * Example usage with streaming
- *
- * ```typescript
- * import { createA3MProvider } from '@a3m/vercel-ai';
- * import { streamText } from 'ai';
- *
- * const a3m = createA3MProvider();
- *
- * const result = await streamText({
- *   model: a3m('auto'),
- *   prompt: 'Write a story about a robot...',
- * });
- *
- * // Stream to response
- * return result.toDataStreamResponse();
- * ```
- */
-//# sourceMappingURL=index.js.map

package/packages/a3m-vercel-ai/dist/index.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAGH,OAAO,EAAE,sBAAsB,EAAE,MAAM,sBAAsB,CAAC;AAI9D,OAAO,EAAE,sBAAsB,EAAE,MAAM,sBAAsB,CAAC;AAe9D;;GAEG;AACH,MAAM,UAAU,iBAAiB,CAAC,SAA0B,EAAE;IAC5D,MAAM,aAAa,GAAG,sBAAsB,CAAC,MAAM,CAAC,CAAC;IAErD,MAAM,QAAQ,GAAG,MAAM,CAAC,MAAM,CAC5B,CAAC,OAAe,EAAE,EAAE;QAClB,qEAAqE;QACrE,OAAO,aAAa,CAAC;IACvB,CAAC,EACD;QACE,IAAI,EAAE,KAAc;QACpB,2CAA2C;QAC3C,QAAQ,EAAE,MAAM;KACjB,CACF,CAAC;IAEF,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH;;;;;;;;;;;;;;;;;GAiBG"}

package/packages/a3m-vercel-ai/dist/types.d.ts

@@ -1,97 +0,0 @@
-/**
- * A3M Router configuration for Vercel AI SDK
- */
-export interface A3MRouterConfig {
-    /**
-     * A3M Router endpoint
-     * @default 'http://localhost:8787'
-     */
-    baseURL?: string;
-    /**
-     * API key for A3M Router
-     * @default 'not-needed' for local
-     */
-    apiKey?: string;
-    /**
-     * Enable parallel ensemble execution
-     * Runs multiple providers and picks the best result
-     * @default false
-     */
-    parallelEnsemble?: boolean;
-    /**
-     * Number of providers to run in parallel when parallelEnsemble is true
-     * @default 3
-     */
-    parallelCount?: number;
-    /**
-     * Enable stealth mode (anti-detection for browser automation)
-     * @default false
-     */
-    stealth?: boolean;
-    /**
-     * Cache configuration
-     */
-    cache?: {
-        enabled?: boolean;
-        ttl?: number;
-    };
-    /**
-     * Provider configuration
-     * Maps provider names to their API keys
-     */
-    providers?: Record<string, {
-        apiKey: string;
-        /** Override the base URL for this provider */
-        baseURL?: string;
-    }>;
-    /**
-     * Cost limits per provider
-     */
-    budgetLimits?: Record<string, {
-        maxCostPerRequest?: number;
-        maxRequestsPerMinute?: number;
-    }>;
-}
-/**
- * A3M Router response from /route or /generate
- */
-export interface A3MRouteResponse {
-    /** The generated content */
-    content: string;
-    /** The provider that was selected */
-    provider: string;
-    /** The model that was used */
-    model: string;
-    /** Cost in USD */
-    cost: number;
-    /** Latency in ms */
-    latencyMs: number;
-    /** Token usage */
-    usage?: {
-        promptTokens: number;
-        completionTokens: number;
-        totalTokens: number;
-    };
-    /** Confidence score (0-1) */
-    confidence?: number;
-    /** Finish reason */
-    finishReason?: 'stop' | 'length' | 'error';
-}
-/**
- * A3M Router streaming response chunk
- */
-export interface A3MStreamChunk {
-    /** The delta content */
-    delta: string;
-    /** Provider that responded */
-    provider: string;
-    /** Whether this is the final chunk */
-    done: boolean;
-    /** Token usage (only on final chunk) */
-    usage?: {
-        promptTokens: number;
-        completionTokens: number;
-        totalTokens: number;
-    };
-}
-//# sourceMappingURL=types.d.ts.map

package/packages/a3m-vercel-ai/dist/types.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,MAAM,WAAW,eAAe;IAC9B;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IAEjB;;;OAGG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAEhB;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,OAAO,CAAC;IAE3B;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IAEvB;;;OAGG;IACH,OAAO,CAAC,EAAE,OAAO,CAAC;IAElB;;OAEG;IACH,KAAK,CAAC,EAAE;QACN,OAAO,CAAC,EAAE,OAAO,CAAC;QAClB,GAAG,CAAC,EAAE,MAAM,CAAC;KACd,CAAC;IAEF;;;OAGG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE;QACzB,MAAM,EAAE,MAAM,CAAC;QACf,8CAA8C;QAC9C,OAAO,CAAC,EAAE,MAAM,CAAC;KAClB,CAAC,CAAC;IAEH;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE;QAC5B,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAC3B,oBAAoB,CAAC,EAAE,MAAM,CAAC;KAC/B,CAAC,CAAC;CACJ;AAED;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAC/B,4BAA4B;IAC5B,OAAO,EAAE,MAAM,CAAC;IAEhB,qCAAqC;IACrC,QAAQ,EAAE,MAAM,CAAC;IAEjB,8BAA8B;IAC9B,KAAK,EAAE,MAAM,CAAC;IAEd,kBAAkB;IAClB,IAAI,EAAE,MAAM,CAAC;IAEb,oBAAoB;IACpB,SAAS,EAAE,MAAM,CAAC;IAElB,kBAAkB;IAClB,KAAK,CAAC,EAAE;QACN,YAAY,EAAE,MAAM,CAAC;QACrB,gBAAgB,EAAE,MAAM,CAAC;QACzB,WAAW,EAAE,MAAM,CAAC;KACrB,CAAC;IAEF,6BAA6B;IAC7B,UAAU,CAAC,EAAE,MAAM,CAAC;IAEpB,oBAAoB;IACpB,YAAY,CAAC,EAAE,MAAM,GAAG,QAAQ,GAAG,OAAO,CAAC;CAC5C;AAED;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,wBAAwB;IACxB,KAAK,EAAE,MAAM,CAAC;IAEd,8BAA8B;IAC9B,QAAQ,EAAE,MAAM,CAAC;IAEjB,sCAAsC;IACtC,IAAI,EAAE,OAAO,CAAC;IAEd,wCAAwC;IACxC,KAAK,CAAC,EAAE;QACN,YAAY,EAAE,MAAM,CAAC;QACrB,gBAAgB,EAAE,MAAM,CAAC;QACzB,WAAW,EAAE,MAAM,CAAC;KACrB,CAAC;CACH"}

package/packages/a3m-vercel-ai/dist/types.js

@@ -1,5 +0,0 @@
-/**
- * A3M Router configuration for Vercel AI SDK
- */
-export {};
-//# sourceMappingURL=types.js.map

package/packages/a3m-vercel-ai/dist/types.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA;;GAEG"}

package/python/a3m_router.egg-info/PKG-INFO

@@ -1,172 +0,0 @@
-Metadata-Version: 2.4
-Name: a3m-router
-Version: 2.2.2
-Summary: Auto-selects cheapest capable LLM from 47+ providers — 70-95% cost savings
-License: MIT
-Project-URL: Homepage, https://github.com/Das-rebel/a3m-router
-Project-URL: Documentation, https://das-rebel.github.io/a3m-router
-Project-URL: Repository, https://github.com/Das-rebel/a3m-router
-Project-URL: Changelog, https://github.com/Das-rebel/a3m-router/releases
-Keywords: llm,routing,openai,proxy,ai-gateway,routellm,litellm,multi-llm,model-selection,cost-optimization,langchain,llamaindex,rag,vector-search,embeddings,parallel,ensemble,router
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: httpx>=0.24.0
-Provides-Extra: langchain
-Requires-Dist: langchain>=0.1.0; extra == "langchain"
-Provides-Extra: llamaindex
-Requires-Dist: llamaindex>=0.9.0; extra == "llamaindex"
-Provides-Extra: qdrant
-Requires-Dist: qdrant-client>=1.7.0; extra == "qdrant"
-Provides-Extra: weaviate
-Requires-Dist: weaviate-client>=4.0.0; extra == "weaviate"
-Provides-Extra: adapters
-Requires-Dist: langchain>=0.1.0; extra == "adapters"
-Requires-Dist: llamaindex>=0.9.0; extra == "adapters"
-Requires-Dist: qdrant-client>=1.7.0; extra == "adapters"
-Requires-Dist: weaviate-client>=4.0.0; extra == "adapters"
-Provides-Extra: dev
-Requires-Dist: pytest>=7.4.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-
-# A3M Router Python SDK
-
-**Intelligent LLM routing — auto-selects the cheapest capable model from 47+ providers.**
-
-Routes queries to the best model for your needs — whether it's Groq for simple Q&A ($0.001/1K) or GPT-4o for complex reasoning ($0.15/1K).
-
-## Installation
-
-```bash
-pip install a3m-router
-```
-
-## Quick Start
-
-```python
-from a3m import A3MRouter
-
-router = A3MRouter(base_url="http://localhost:8787")
-
-# Auto-routes to optimal provider
-response = await router.chat("What is 2+2?")
-# → Routes to Groq, costs ~$0.000001
-
-# See routing decision before executing
-decision = await router.route("Explain quantum computing")
-print(f"Model: {decision.model}")
-print(f"Tier: {decision.tier}")
-print(f"Cost: ${decision.cost:.6f}")
-
-# Stream responses
-async for token in router.stream_chat("Tell me a story"):
-    print(token, end="", flush=True)
-```
-
-## Key Features
-
-- **Auto-routing**: Picks the right model based on query complexity, budget, and requirements
-- **Cost savings**: 70-95% cheaper than always using premium models
-- **47+ providers**: Groq, DeepSeek, GPT-4o, Claude, Mistral, and more
-- **Framework adapters**: Drop-in for LangChain, LlamaIndex, Qdrant, Weaviate
-- **Health monitoring**: Check provider status and availability
-- **Cost analytics**: Track spending and savings
-
-## Framework Adapters
-
-| Adapter | Use Case | Install |
-|---------|----------|---------|
-| **LangChain** | Chain-based AI workflows | `pip install a3m-router[langchain]` |
-| **LlamaIndex** | RAG and document QA | `pip install a3m-router[llamaindex]` |
-| **Qdrant** | Vector search + RAG | `pip install a3m-router[qdrant]` |
-| **Weaviate** | Vector search + RAG | `pip install a3m-router[weaviate]` |
-
-All adapters:
-```bash
-pip install a3m-router[all]
-```
-
-## Routing Tiers
-
-| Tier | Providers | Cost | When Used |
-|------|-----------|------|-----------|
-| **free** | Ollama, vLLM | $0 | Local inference |
-| **cheap** | Groq, DeepSeek | ~$0.001/1K | Simple Q&A, short code |
-| **mid** | GPT-4o-mini, Claude-haiku | ~$0.01/1K | Standard tasks |
-| **premium** | GPT-4o, Claude-sonnet | ~$0.15/1K | Complex reasoning |
-
-## API Reference
-
-### A3MRouter
-
-```python
-router = A3MRouter(
-    base_url="http://localhost:8787",  # A3M Router server URL
-    timeout=30.0,                       # Request timeout
-)
-```
-
-| Method | Description |
-|--------|-------------|
-| `chat(message)` | Send chat message with auto-routing |
-| `route(query)` | Get routing decision (no execution) |
-| `route_batch(queries)` | Route multiple queries |
-| `stream_chat(message)` | Stream response tokens |
-| `models()` | List all available models |
-| `health()` | Provider health status |
-| `cost_report()` | Cost analytics |
-
-### LangChain Example
-
-```python
-from a3m import LangChainAdapter
-from langchain.schema import HumanMessage
-
-llm = LangChainAdapter(base_url="http://localhost:8787")
-response = llm([HumanMessage(content="What is RAG?")])
-```
-
-### LlamaIndex Example
-
-```python
-from a3m import LlamaIndexAdapter
-
-llm = LlamaIndexAdapter()
-response = llm.complete("Explain transformers")
-```
-
-## Server Setup
-
-Start the A3M Router server:
-
-```bash
-# Via npm
-npx a3m-router serve
-
-# Via Docker
-docker-compose up -d
-```
-
-Server runs on `http://localhost:8787` by default.
-
-## Links
-
-- **GitHub**: https://github.com/Das-rebel/a3m-router
-- **npm Package**: https://www.npmjs.com/package/adaptive-memory-multi-model-router
-- **Documentation**: https://das-rebel.github.io/a3m-router
-
-## License
-
-MIT

package/python/a3m_router.egg-info/SOURCES.txt

@@ -1,17 +0,0 @@
-README.md
-pyproject.toml
-setup.py
-a3m/__init__.py
-a3m/client.py
-a3m/models.py
-a3m/sync_client.py
-a3m/adapters/__init__.py
-a3m/adapters/langchain.py
-a3m/adapters/llamaindex.py
-a3m/adapters/qdrant.py
-a3m/adapters/weaviate.py
-a3m_router.egg-info/PKG-INFO
-a3m_router.egg-info/SOURCES.txt
-a3m_router.egg-info/dependency_links.txt
-a3m_router.egg-info/requires.txt
-a3m_router.egg-info/top_level.txt

package/python/a3m_router.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

package/python/a3m_router.egg-info/requires.txt

@@ -1,24 +0,0 @@
-httpx>=0.24.0
-
-[adapters]
-langchain>=0.1.0
-llamaindex>=0.9.0
-qdrant-client>=1.7.0
-weaviate-client>=4.0.0
-
-[dev]
-pytest>=7.4.0
-pytest-asyncio>=0.21.0
-black>=23.0.0
-
-[langchain]
-langchain>=0.1.0
-
-[llamaindex]
-llamaindex>=0.9.0
-
-[qdrant]
-qdrant-client>=1.7.0
-
-[weaviate]
-weaviate-client>=4.0.0

package/python/a3m_router.egg-info/top_level.txt

@@ -1 +0,0 @@
-a3m