gpt-researcher v3.7.0

Smarter context, no embeddings required

GPT Researcher now picks the context it sends to the LLM by usefulness, not similarity. Every passage scraped for a research question is scored by Jev on how useful it is for answering that question, and only the passages that help are kept.

On a benchmark of 28 research tasks replayed on identical sources:

Nothing is required. With TYPESAFE_API_KEY set, Jev is used. Without one, or if a Jev call fails, GPT Researcher falls back to local keyword (BM25) ranking, so you no longer need an embeddings provider for standard research. Report chat uses the same filter.

• Docs: https://docs.gptr.dev/docs/gpt-researcher/gptr/context-filter
• Benchmark, method and code: evals/context_filter/

⚠️ Changes to note

• Python 3.12+ is now required.
• Default context filter: without a TypeSafe key, the default is now keyword ranking instead of embeddings. It matched or beat embeddings on every measure in the benchmark. To keep the old behaviour, set CONTEXT_FILTER=embeddings.

Also in this release

• Retriever plugins: ship a search provider as its own package via the gpt_researcher.retrievers entry point (#2154)
• Fixed the frontend WebSocket opening a second connection on a new research run (#2159)
• Multi-agent sections no longer repeat each other’s content (#2158)
• Self-hosted frontend assets, no third-party CDNs (#2082)
• 25+ community fixes across retrievers, scrapers and deep research
• Docs: redesigned homepage, current model hallucination leaderboard, fixed builds on fresh installs

Install: pip install -U gpt-researcher (0.16.0)

What’s Changed

• fix: define stream output for multi-agent execution by @alaningtrump in https://github.com/assafelovic/gpt-researcher/pull/2092
• fix(deps): pin mcp below 2.0 to keep MCPRetriever importable by @DAI-BZ in https://github.com/assafelovic/gpt-researcher/pull/2147
• fix(bing): bound request and handle transport failures by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2133
• fix(semantic-scholar): bound request and guard response parsing by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2130
• fix(openalex): handle malformed JSON responses by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2128
• fix(multi-agents): load .env before tracing setup by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2126
• fix: preserve caller-provided empty visited_urls set by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2122
• fix: handle zero generated queries in deep research by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2111
• fix: reject whitespace-only deep research query fields by @L4XB in https://github.com/assafelovic/gpt-researcher/pull/2117
• fix(google): filter YouTube hosts case-insensitively by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2113
• fix(retrievers): fall back after blank normalization by @remote-controlled-man in https://github.com/assafelovic/gpt-researcher/pull/2105
• fix(research): preserve complementary web context by @remote-controlled-man in https://github.com/assafelovic/gpt-researcher/pull/2104
• fix(research): record prefetched URLs in visited_urls by @feiiiiii5 in https://github.com/assafelovic/gpt-researcher/pull/2123
• fix(research): preserve initial planning sources in report context by @guybass in https://github.com/assafelovic/gpt-researcher/pull/2145
• fix(mcp): detect URL schemes case-insensitively by @anupamking01 in https://github.com/assafelovic/gpt-researcher/pull/2114
• fix(chat): preserve sources from the actual search tool invocation by @beemines in https://github.com/assafelovic/gpt-researcher/pull/2112
• fix(scraper): keep inline text in its line when extracting page text by @L4XB in https://github.com/assafelovic/gpt-researcher/pull/2149
• fix(llm): let llm_kwargs / LLM_KWARGS override the computed temperature by @rbales79 in https://github.com/assafelovic/gpt-researcher/pull/2107
• fix: correct typos in user-facing warnings, subtopic prompt, and docstring by @feizhuzheng in https://github.com/assafelovic/gpt-researcher/pull/2080
• Make Serper retriever base URL configurable via SERPER_API_BASE by @starnikovoleg in https://github.com/assafelovic/gpt-researcher/pull/2103
• fix(frontend): self-host browser assets by @ousamabenyounes in https://github.com/assafelovic/gpt-researcher/pull/2082
• docs: fix dead retrievers link in hybrid research example by @yetuge in https://github.com/assafelovic/gpt-researcher/pull/2136
• docs: add Russian README translation by @MonteNegroX in https://github.com/assafelovic/gpt-researcher/pull/2083
• chore(deps): update numpy requirement from <2.3.0,>=2.0.0 to >=2.0.0,<2.5.0 by @dependabot[bot] in https://github.com/assafelovic/gpt-researcher/pull/2087
• chore(deps): update deepagents requirement from >=0.6 to >=0.7.8 by @dependabot[bot] in https://github.com/assafelovic/gpt-researcher/pull/2085
• chore: untrack maintainer triage notes; stop dependabot raising floors by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2151
• feat(retrievers): load third-party retrievers from entry points by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2154
• chore(deps): update numpy requirement from <2.3.0,>=2.0.0 to >=2.0.0,<2.5.0 by @dependabot[bot] in https://github.com/assafelovic/gpt-researcher/pull/2155
• Bump python from 3.12-slim-bookworm to 3.14-slim-bookworm by @dependabot[bot] in https://github.com/assafelovic/gpt-researcher/pull/1612
• fix(document): tolerate missing metadata source on loaded pages by @Bartok9 in https://github.com/assafelovic/gpt-researcher/pull/2152
• Add quality_eval: ground-truth-free report quality evaluation by @SeanHe727 in https://github.com/assafelovic/gpt-researcher/pull/1821
• fix: carry over the remaining fixes from #2140 and #2121 by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2157
• fix(multi_agents): tell each parallel section what its siblings cover by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2158
• fix(websocket): stop a new research run from opening a second socket by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2159
• ci: don’t fail fork PRs on the LLM cost comment by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2160
• feat(context): filter scraped content with Jev; embeddings become optional by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2161
• feat(context): keyword fallback so no filter needs a key or embeddings by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2162
• docs: current model leaderboard; fix the docs build on fresh installs by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2170
• docs: redesign the documentation homepage by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2171
• docs(homepage): drop the code card and stats strip; centre the hero by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2172
• docs(homepage): restore the two-column hero by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2173

New Contributors

• @alaningtrump made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2092
• @DAI-BZ made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2147
• @anupamking01 made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2133
• @L4XB made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2117
• @remote-controlled-man made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2105
• @feiiiiii5 made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2123
• @guybass made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2145
• @beemines made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2112
• @rbales79 made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2107
• @feizhuzheng made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2080
• @starnikovoleg made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2103
• @ousamabenyounes made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2082
• @yetuge made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2136
• @MonteNegroX made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2083
• @Bartok9 made their first contribution in https://github.com/assafelovic/gpt-researcher/pull/2152

Full Changelog: https://github.com/assafelovic/gpt-researcher/compare/v3.6.1…v3.7.0

---

Source assafelovic/gpt-researcher · v3.7.0 · 2026-09-26 · upstream release

Mirrored verbatim for indexing. All rights belong to the upstream project.