# private-gpt | Zylon | Knowledge Base | Instagit

Interact with your documents using the power of GPT, 100% privately, no data leaks

GitHub Stars: 57.2k

Repository: https://github.com/zylon-ai/private-gpt

---

## Articles

### [Troubleshooting Poor RAG Retrieval Results in PrivateGPT: A Complete Guide](/zylon-ai/private-gpt/troubleshoot-rag-retrieval-privategpt)

Troubleshoot poor RAG retrieval in PrivateGPT. Learn to fix mismatched embedding models, optimize similarity_top_k, manage doc_id metadata, and re-ingest vector indices for better results.

- Tags: how-to-guide
- Published: 2026-03-06

### [Handling Large Document Ingestion Using Parallel Processing Modes in PrivateGPT](/zylon-ai/private-gpt/privategpt-large-document-ingestion-strategies)

Discover how to efficiently process massive document collections with PrivateGPT"s parallel processing modes. Optimize your ingestion scaling for seamless large document handling.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Configure Similarity Thresholds for Filtering RAG Retrieval Results in PrivateGPT](/zylon-ai/private-gpt/privategpt-configure-similarity-thresholds)

Configure PrivateGPT similarity thresholds to filter RAG retrieval results. Learn how similarity_top_k and similarity_value enhance relevancy and optimize your chatbot's performance.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Use the PrivateGPT Low-Level Embeddings API for Custom RAG Pipelines](/zylon-ai/private-gpt/how-to-use-privategpt-embeddings-api)

Learn to use PrivateGPT's low-level embeddings API to create custom RAG pipelines. Integrate dense vectors into your bespoke generation workflows via the OpenAI-compatible endpoint.

- Tags: how-to-guide
- Published: 2026-03-06

### [PrivateGPT Dependency Injection Architecture: How Components Are Wired Together](/zylon-ai/private-gpt/privategpt-dependency-injection-architecture)

Explore PrivateGPTs dependency injection architecture. Learn how its three-layer system using the injector library wires components together for efficient runtime object management.

- Tags: architecture
- Published: 2026-03-06

### [How PrivateGPT's File Watcher Automates Document Ingestion in Real-Time](/zylon-ai/private-gpt/privategpt-file-watcher-document-ingestion)

Discover how PrivateGPT's file watcher automates real-time document ingestion by automatically triggering Llama-Index to embed and store new files in the vector database.

- Tags: internals
- Published: 2026-03-06

### [How to Configure Node Storage Backends in PrivateGPT: Simple File vs PostgreSQL](/zylon-ai/private-gpt/privategpt-node-storage-backends)

Configure PrivateGPT node storage backends easily. Learn to set up simple file storage or PostgreSQL for your Zylon AI private-gpt repository. Maximize data control.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Configure Prompt Styles in Private-GPT: Llama 2, Llama 3, Mistral, ChatML, and Tag](/zylon-ai/private-gpt/privategpt-prompt-style-configuration)

Learn to configure prompt styles in PrivateGPT, including Llama 2, Llama 3, Mistral, ChatML, and Tag. Format your chat messages effectively for LLM compatibility.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Enable and Implement Streaming Responses for Chat and Completion Endpoints in PrivateGPT](/zylon-ai/private-gpt/how-to-implement-streaming-responses-privategpt)

Enable streaming responses in PrivateGPT for chat and completion endpoints. Learn how to use SSE for incremental token delivery instead of full JSON payloads. Optimize your applications today.

- Tags: how-to-guide
- Published: 2026-03-06

### [How the Health Check Endpoint Functions in PrivateGPT for System Monitoring](/zylon-ai/private-gpt/privategpt-health-check-endpoint)

Learn how the PrivateGPT health check endpoint at /health monitors your system. This simple GET route confirms API server responsiveness with a quick JSON status check.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Implement Context Filtering in Private-GPT to Restrict RAG Responses to Specific Documents](/zylon-ai/private-gpt/privategpt-context-filtering-documents)

Secure your RAG responses with Private-GPT context filtering. Learn how to restrict retrieval to specific documents using the ContextFilter for enhanced privacy and control.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Tune LLM Generation Parameters in PrivateGPT: Temperature, Top-k, Top-p, and Repeat Penalty](/zylon-ai/private-gpt/how-to-tune-llm-parameters-privategpt)

Master LLM generation parameters in PrivateGPT. Learn to tune temperature, max_tokens, top_k, top_p, and repeat_penalty for optimal AI output by editing settings models.

- Tags: how-to-guide
- Published: 2026-03-06

### [Deploying PrivateGPT Using Docker and Docker Compose: A Complete Guide](/zylon-ai/private-gpt/deploy-privategpt-with-docker)

Easily deploy PrivateGPT with Docker and docker-compose. Clone the zylon-ai/private-gpt repo, choose your backend, and run a simple command to start your private AI assistant.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Use the PrivateGPT Summarization Recipe API: Complete HTTP Endpoint Guide](/zylon-ai/private-gpt/how-to-use-privategpt-summarization-api)

Discover how to use the PrivateGPT summarization recipe API. Access the /v1/summarize HTTP endpoint to generate concise summaries from your documents effortlessly.

- Tags: api-reference
- Published: 2026-03-06

### [How to Use the Low-Level Chunks API for Custom Retrieval Logic in RAG](/zylon-ai/private-gpt/how-to-use-privategpt-chunks-api)

Master the PrivateGPT Chunks API to build custom RAG pipelines. Query document fragments directly for efficient retrieval logic without LLM inference.

- Tags: how-to-guide
- Published: 2026-03-06

### [Configuring Embedding Models in Private-GPT: HuggingFace, OpenAI, Ollama, and Mistral Options](/zylon-ai/private-gpt/privategpt-embedding-model-configuration)

Explore embedding model options for Private-GPT. Learn to configure HuggingFace, OpenAI, Ollama, and Mistral backends using settings.yaml for seamless integration.

- Tags: configuration
- Published: 2026-03-06

### [How Reranking Is Implemented and Configured in the PrivateGPT RAG Pipeline with Sentence Transformers](/zylon-ai/private-gpt/privategpt-rag-reranking-setup)

Learn how PrivateGPT implements reranking in its RAG pipeline with Sentence Transformers. Discover how to configure this feature to reorder documents by relevance before LLM context assembly.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Enable and Customize the Gradio User Interface for Testing and Interaction in Private‑GPT](/zylon-ai/private-gpt/how-to-enable-customize-gradio-ui-privategpt)

Learn to enable and customize the Gradio User Interface in Private-GPT. Easily configure settings and run the application for seamless interaction and testing.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Configure CORS Settings to Allow Cross-Origin Requests in Private-GPT](/zylon-ai/private-gpt/privategpt-configure-cors-settings)

Learn how to configure CORS settings in Private-GPT to allow cross-origin requests. Easily enable and define access rules in your YAML file for seamless API integration.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Enable and Configure API Authentication in PrivateGPT: A Complete Guide](/zylon-ai/private-gpt/privategpt-api-authentication-setup)

Secure your PrivateGPT API by enabling and configuring authentication. Learn how to set up header validation and protect your routes with this comprehensive guide.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Use the High-Level RAG Chat API in PrivateGPT for Conversational Context](/zylon-ai/private-gpt/how-to-use-privategpt-rag-chat-api)

Learn to use PrivateGPT's high-level RAG chat API with ChatService for conversational context from ingested documents. Explore chat() and stream_chat() with use_context=True.

- Tags: tutorial
- Published: 2026-03-06

### [How the PrivateGPT Document Ingestion Pipeline Works: Simple, Batch, Parallel, and Pipeline Modes](/zylon-ai/private-gpt/privategpt-document-ingestion-pipeline-modes)

Discover how PrivateGPT's document ingestion pipeline optimizes processing with simple, batch, parallel, and pipeline modes. Learn about its pluggable architecture and configuration settings.

- Tags: internals
- Published: 2026-03-06

### [Vector Database Options in Private-GPT: How to Configure Qdrant, Chroma, Postgres, ClickHouse, and Milvus](/zylon-ai/private-gpt/privategpt-vector-database-setup)

Explore vector database options for Private-GPT including Qdrant, Chroma, Postgres, ClickHouse, and Milvus. Learn how to easily configure and set up your preferred backend.

- Tags: how-to-guide
- Published: 2026-03-06

### [How to Configure PrivateGPT with Different LLM Providers: Ollama, OpenAI, Azure, SageMaker, and Gemini](/zylon-ai/private-gpt/how-to-configure-privategpt-llm-providers)

Configure PrivateGPT with Ollama OpenAI Azure SageMaker Gemini by setting llm.mode. Learn to integrate custom LLMs easily for enhanced local AI interactions.

- Tags: how-to-guide
- Published: 2026-03-06