deepsearch-academic

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Framework

Streamlit

AI

OpenAI SDK, LangChain, LangGraph

API layer

Pydantic

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  LLM relevance filteran LLM yes/no relevance check
• AI
  Grounded conversational QAanswers are grounded in retrieved nodes only
• AI
  llama.cpp OpenAI APIllama.cpp `llama-server` over its OpenAI-compatible `/v1` API
• AI
  Local embeddings endpointEmbeddings need pooling enabled (`--embeddings`)
• API
  Semantic Scholar searchSemantic Scholar bulk search (or a built-in mock corpus in debug mode)
• Data
  RAPTOR summary treecluster chunks, summarize clusters, repeat until one root
• Data
  FAISS tree retrievalretrieve from the full tree via FAISS
• Deploy
  Docker deploymentThe app container defaults `LLAMA_CPP_BASE_URL` to `http://host.docker.internal:8080/v1`
• Deploy
  Docker compose LLM profileOptional compose profile `llm` starts `ghcr.io/ggml-org/llama.cpp:server`
• Other
  PDF report exportacademic-style PDF report, pipeline Mermaid diagram, and a bibliography
• Other
  Mermaid diagram exportpipeline Mermaid diagram
• Other
  Bibliography exporta bibliography of kept and discarded papers
• Testing
  Offline test suiteThe default suite is offline
• UI
  Streamlit interfaceStreamlit is only the UI

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.