# deep-searcher - Doramagic AI Context Pack > Purpose: pre-work context for the user's host AI. This pack does not prove that the project has been installed, run, or validated. ## Project - canonical_name: `zilliztech/deep-searcher` - capability: Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python. - expected_user_outcome: Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python. ## Operating Boundaries - Do not claim that the project has been installed, run, called through an API, or used on local files unless separate evidence proves it. - Project facts must come from repo evidence, Claim Graph, or explicit source references. - When a capability is not verified, mark it as unverified instead of completing it as fact. - publish_status: `publishable` - blocking_gaps: none --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Project Overview & System Architecture**: importance `high` - source_paths: README.md, deepsearcher/__init__.py, deepsearcher/configuration.py, deepsearcher/config.yaml, deepsearcher/agent/base.py - **Installation & Quickstart**: importance `high` - source_paths: README.md, pyproject.toml, env.example, main.py, deepsearcher/cli.py - **LLM Provider Configuration**: importance `high` - source_paths: deepsearcher/llm/__init__.py, deepsearcher/llm/base.py, deepsearcher/llm/openai_llm.py, deepsearcher/llm/deepseek.py, deepsearcher/llm/anthropic_llm.py - **Embedding Model Configuration**: importance `high` - source_paths: deepsearcher/embedding/__init__.py, deepsearcher/embedding/base.py, deepsearcher/embedding/milvus_embedding.py, deepsearcher/embedding/openai_embedding.py, deepsearcher/embedding/voyage_embedding.py - **Vector Database & Data Loader Configuration**: importance `high` - source_paths: deepsearcher/vector_db/__init__.py, deepsearcher/vector_db/base.py, deepsearcher/vector_db/milvus.py, deepsearcher/vector_db/azure_search.py, deepsearcher/vector_db/oracle.py - **RAG Agent System & Retrieval Strategies**: importance `high` - source_paths: deepsearcher/agent/base.py, deepsearcher/agent/naive_rag.py, deepsearcher/agent/chain_of_rag.py, deepsearcher/agent/deep_search.py, deepsearcher/agent/collection_router.py - **Deployment, CLI & FastAPI Service**: importance `medium` - source_paths: deepsearcher/cli.py, main.py, Dockerfile, Makefile, evaluation/evaluate.py - **Extensibility, Troubleshooting & FAQ**: importance `high` - source_paths: docs/contributing/index.md, docs/faq/index.md, docs/future_plans.md, CONTRIBUTING.md, deepsearcher/llm/base.py ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `d89e37cdfbbef5e44ae6162ce9cc2c627a69b7e1` - inspected_files: `Dockerfile`, `README.md`, `pyproject.toml`, `uv.lock`, `docs/README.md`, `docs/configuration/embedding.md`, `docs/configuration/file_loader.md`, `docs/configuration/index.md`, `docs/configuration/llm.md`, `docs/configuration/vector_db.md`, `docs/configuration/web_crawler.md`, `docs/contributing/index.md`, `docs/examples/basic_example.md`, `docs/examples/docling.md`, `docs/examples/firecrawl.md`, `docs/examples/index.md`, `docs/examples/oracle.md`, `docs/examples/unstructured.md`, `docs/faq/index.md`, `docs/future_plans.md` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Configuration risk requires verification - Trigger: Project evidence flags a configuration risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: community_evidence:github | https://github.com/zilliztech/deep-searcher/issues/255 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Installation risk requires verification - Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: community_evidence:github | https://github.com/zilliztech/deep-searcher/issues/270 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Installation risk requires verification - Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: community_evidence:github | https://github.com/zilliztech/deep-searcher/issues/67 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Configuration risk requires verification - Trigger: Project evidence flags a configuration risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.host_targets | https://github.com/zilliztech/deep-searcher - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/zilliztech/deep-searcher - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 6: Maintenance risk requires verification - Trigger: Project evidence flags a maintenance risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/zilliztech/deep-searcher - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 7: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/zilliztech/deep-searcher - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 8: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/zilliztech/deep-searcher - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 9: Security or permission risk requires verification - Trigger: Project evidence flags a security or permission risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: community_evidence:github | https://github.com/zilliztech/deep-searcher/issues/254 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 10: Security or permission risk requires verification - Trigger: Project evidence flags a security or permission risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: community_evidence:github | https://github.com/zilliztech/deep-searcher/issues/267 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.