Python integrations
Output that fits your existing stack.
Drop LLMSlim into a LangChain, LlamaIndex or Haystack pipeline, or pass its output straight into the model client you already use. Provider calls stay in your application.
LLM Provider
- SarvamStartup Program memberAdaptive context planning meets Sarvam’s Indic language models and language tools.
- OpenAIPython integrationCompress Python application context before an OpenAI SDK request.
- AnthropicPython integrationPrepare long Python-managed context before an Anthropic SDK request.
- Google GeminiPython integrationCompress retrieved Python context before a Gemini SDK request.
Framework
- LangChainDocument compressorA BaseDocumentCompressor for ContextualCompressionRetriever. Use it where you would use LLMLinguaCompressor.
- LlamaIndexNode postprocessorA BaseNodePostprocessor for query engines. Use it where you would use LongLLMLinguaPostprocessor.
- HaystackPipeline componentA Haystack 2.x and 3 component that compresses retrieved documents between the retriever and the prompt builder.
Backend Services
- ZohoEnterprise contextBounded, read-only CRM and WorkDrive context for planning.
- MongoDBMemory & retrievalExplicit persistent context, Atlas retrieval, and hosted quota accounting.
- ExaWeb search contextLive web search results as bounded, untrusted context for planning.
- Neo4jGraph memoryTemporal agent memory where newer facts supersede old ones, with an audit trail.