Metadata-Version: 2.5
Name: warm-integrations
Version: 0.1.0
Summary: Agent and RAG framework adapters for WARM
Project-URL: Homepage, https://github.com/writerslogic/warm/blob/main/docs/integrations/index.md
Project-URL: Repository, https://github.com/writerslogic/warm
Project-URL: Issues, https://github.com/writerslogic/warm/issues
Author-email: "WritersLogic, Inc." <david@writerslogic.com>
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agent-memory,langchain,llamaindex,rag,vector-store,warm,writerslogic
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: httpx>=0.27
Requires-Dist: warm-sdk>=0.1.3
Provides-Extra: ag2
Requires-Dist: ag2>=1.1.2; extra == 'ag2'
Provides-Extra: autogen
Requires-Dist: autogen-agentchat>=0.7.5; extra == 'autogen'
Requires-Dist: autogen-core>=0.7.5; extra == 'autogen'
Requires-Dist: autogen-ext>=0.7.5; extra == 'autogen'
Provides-Extra: crewai
Requires-Dist: crewai>=1.15.28; extra == 'crewai'
Provides-Extra: dspy
Requires-Dist: dspy>=3.4.1; extra == 'dspy'
Requires-Dist: filelock>=4.2.6; extra == 'dspy'
Requires-Dist: numpy; extra == 'dspy'
Provides-Extra: haystack
Requires-Dist: haystack-ai>=3.4.0; extra == 'haystack'
Provides-Extra: langchain
Requires-Dist: langchain-core>=1.6.12; extra == 'langchain'
Requires-Dist: numpy; extra == 'langchain'
Provides-Extra: langgraph
Requires-Dist: langgraph-checkpoint>=4.3.0; extra == 'langgraph'
Requires-Dist: langgraph>=1.2.16; extra == 'langgraph'
Provides-Extra: letta
Requires-Dist: letta-client>=1.12.1; extra == 'letta'
Provides-Extra: litellm
Requires-Dist: filelock>=4.2.6; extra == 'litellm'
Requires-Dist: litellm>=1.103.10; extra == 'litellm'
Requires-Dist: mcp>=2.3.0; extra == 'litellm'
Provides-Extra: llamaindex
Requires-Dist: llama-index-core>=0.14.25; extra == 'llamaindex'
Provides-Extra: mem0
Requires-Dist: mem0ai>=2.2.1; extra == 'mem0'
Provides-Extra: openai-agents
Requires-Dist: openai-agents>=0.24.0; extra == 'openai-agents'
Provides-Extra: pydantic-ai
Requires-Dist: pydantic-ai-slim>=2.58.0; extra == 'pydantic-ai'
Provides-Extra: semantic-kernel
Requires-Dist: semantic-kernel>=1.45.0; extra == 'semantic-kernel'
Requires-Dist: werkzeug>=3.1.9; extra == 'semantic-kernel'
Provides-Extra: smolagents
Requires-Dist: smolagents>=1.26.0; extra == 'smolagents'
Description-Content-Type: text/markdown

# warm-integrations

Adapters that put WARM behind the memory, vector-store and retriever interfaces of Python agent and RAG frameworks, over the `warm-server` HTTP service.

## Install

Framework dependency trees conflict: install exactly one extra per environment.

```sh
pip install "warm-integrations[langchain]"   # or another extra from the table
warm-server --input-dim 384                               # the vector length your embeddings produce
```

## Quickstart

<!-- quickstart-check: python langchain -->
```python
from langchain_core.documents import Document
from writerslogic_warm_integrations.core import HashingEmbedder
from writerslogic_warm_integrations.langchain import EmbedderAsLangChain, WarmVectorStore

store = WarmVectorStore(EmbedderAsLangChain(HashingEmbedder(384)), url="http://127.0.0.1:8080", api_key="dev", tenant_id="acme", collection="docs")
store.add_documents([Document(page_content="Rust has ownership and borrowing.", metadata={"topic": "code"})], ids=["rust"])
print(store.similarity_search("borrowing", k=4, filter={"topic": "code"}))
```

Run `warm-server --no-auth --input-dim 384` (or set `WARM_API_KEY=dev` and pass `api_key="dev"`) first. `HashingEmbedder` is lexical and offline; pass a real embedding model for semantic search. One runnable offline example per adapter is in `examples/`.

## Options

Every adapter accepts the same WARM settings as keyword arguments or `config=WarmConfig(...)`:

| Name | Type | Default | Meaning |
|---|---|---|---|
| `url`, `api_key`, `timeout`, `transport` | str, str, float, httpx transport | local server | Connection to `warm-server` |
| `tenant_id` | str | default tenant | Separate store per tenant |
| `collection` | str | none | Namespace inside a tenant |
| `embedder` / the framework's embeddings | `Embedder` | `HashingEmbedder(input_dim or 384)` | Encoder; `text_queries=True` lets a model-enabled server embed text |
| `max_fetch` | int | 100 | Result ceiling; match the server's `--max-top-k` |
| `overfetch` | int | 5 | Accepted for compatibility |

## Adapters

| Extra | Host (tested version) | Page |
|---|---|---|
| `langchain` | langchain-core 1.6.12 | [LangChain](../../docs/integrations/frameworks/langchain.md) |
| `langgraph` | langgraph 1.2.16 | [LangGraph](../../docs/integrations/frameworks/langgraph.md) |
| `llamaindex` | llama-index-core 0.14.25 | [LlamaIndex](../../docs/integrations/frameworks/llamaindex.md) |
| `haystack` | haystack-ai 3.4.0 | [Haystack](../../docs/integrations/frameworks/haystack.md) |
| `dspy` | dspy 3.4.1, 3.5.0 | [DSPy](../../docs/integrations/frameworks/dspy.md) |
| `openai-agents` | openai-agents 0.24.0 | [OpenAI Agents](../../docs/integrations/frameworks/openai-agents.md) |
| `pydantic-ai` | pydantic-ai-slim 2.58.0 | [Pydantic AI](../../docs/integrations/frameworks/pydantic-ai.md) |
| `smolagents` | smolagents 1.26.0 | [smolagents](../../docs/integrations/frameworks/smolagents.md) |
| `litellm` | litellm 1.103.10 | [LiteLLM](../../docs/integrations/frameworks/litellm.md) |
| `crewai` | crewai 1.15.28 | [CrewAI](../../docs/integrations/frameworks/crewai.md) |
| `autogen` | autogen 0.7.5 | [AutoGen](../../docs/integrations/frameworks/autogen.md) |
| `ag2` | ag2 1.1.2 | [AutoGen and AG2](../../docs/integrations/frameworks/autogen.md) |
| `semantic-kernel` | semantic-kernel 1.45.0 | [Semantic Kernel](../../docs/integrations/frameworks/semantic-kernel.md) |
| `mem0` | mem0ai 2.2.1 | [mem0](../../docs/integrations/frameworks/mem0.md) |
| `letta` | letta-client 1.12.1 | [Letta](../../docs/integrations/frameworks/letta.md) |

## Compatibility

Python 3.11+ (tested 3.12), `warm-sdk` >= 0.1.3, `warm-server` of the same WARM release. Tests: `WARM_SERVER_BIN=/path/to/warm-server ./run-matrix.sh [extra ...]` (one isolated environment per extra).

## Reference

[Integrations overview](../../docs/integrations/index.md), [verification matrix and shared limits](../../docs/integrations/frameworks/MATRIX.md).
