refactor: improve seed source handling with additional type support, enhanced parsing logic, and text chunking optimization
This commit is contained in:
parent
3e17e2b0f6
commit
424b00b701
8 changed files with 98 additions and 32 deletions
|
|
@ -5,10 +5,10 @@
|
|||
"": {
|
||||
"name": "unsloth-theme",
|
||||
"dependencies": {
|
||||
"@assistant-ui/react": "^0.12.3",
|
||||
"@assistant-ui/react-markdown": "^0.12.1",
|
||||
"@assistant-ui/react-streamdown": "^0.1.0",
|
||||
"@base-ui/react": "^1.1.0",
|
||||
"@assistant-ui/react": "^0.12.10",
|
||||
"@assistant-ui/react-markdown": "^0.12.3",
|
||||
"@assistant-ui/react-streamdown": "^0.1.2",
|
||||
"@base-ui/react": "^1.2.0",
|
||||
"@dagrejs/dagre": "^2.0.4",
|
||||
"@dagrejs/graphlib": "^3.0.4",
|
||||
"@fontsource-variable/figtree": "^5.2.10",
|
||||
|
|
@ -17,6 +17,8 @@
|
|||
"@hugeicons/core-free-icons": "^3.1.1",
|
||||
"@hugeicons/react": "^1.1.5",
|
||||
"@huggingface/hub": "^2.9.0",
|
||||
"@langchain/core": "^1.1.27",
|
||||
"@langchain/textsplitters": "^1.0.1",
|
||||
"@radix-ui/react-checkbox": "^1.3.3",
|
||||
"@radix-ui/react-label": "^2.1.8",
|
||||
"@radix-ui/react-select": "^2.2.6",
|
||||
|
|
@ -65,12 +67,12 @@
|
|||
},
|
||||
"devDependencies": {
|
||||
"@biomejs/biome": "^1.9.4",
|
||||
"@eslint/js": "^9.39.2",
|
||||
"@types/node": "^24.10.13",
|
||||
"@types/react": "^19.2.14",
|
||||
"@eslint/js": "^9.39.1",
|
||||
"@types/node": "^24.10.1",
|
||||
"@types/react": "^19.2.5",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
"@vitejs/plugin-react": "^5.1.4",
|
||||
"eslint": "^9.39.2",
|
||||
"@vitejs/plugin-react": "^5.1.1",
|
||||
"eslint": "^9.39.1",
|
||||
"eslint-plugin-react-hooks": "^7.0.1",
|
||||
"eslint-plugin-react-refresh": "^0.4.26",
|
||||
"globals": "^16.5.0",
|
||||
|
|
@ -181,6 +183,8 @@
|
|||
|
||||
"@braintree/sanitize-url": ["@braintree/sanitize-url@7.1.2", "", {}, "sha512-jigsZK+sMF/cuiB7sERuo9V7N9jx+dhmHHnQyDSVdpZwVutaBu7WvNYqMDLSgFgfB30n452TP3vjDAvFC973mA=="],
|
||||
|
||||
"@cfworker/json-schema": ["@cfworker/json-schema@4.1.1", "", {}, "sha512-gAmrUZSGtKc3AiBL71iNWxDsyUC5uMaKKGdvzYsBoTW/xi42JQHl7eKV2OYzCUqvc+D2RCcf7EXY2iCyFIk6og=="],
|
||||
|
||||
"@chevrotain/cst-dts-gen": ["@chevrotain/cst-dts-gen@11.0.3", "", { "dependencies": { "@chevrotain/gast": "11.0.3", "@chevrotain/types": "11.0.3", "lodash-es": "4.17.21" } }, "sha512-BvIKpRLeS/8UbfxXxgC33xOumsacaeCKAjAeLyOn7Pcp95HiRbrpl14S+9vaZLolnbssPIUuiUd8IvgkRyt6NQ=="],
|
||||
|
||||
"@chevrotain/gast": ["@chevrotain/gast@11.0.3", "", { "dependencies": { "@chevrotain/types": "11.0.3", "lodash-es": "4.17.21" } }, "sha512-+qNfcoNk70PyS/uxmj3li5NiECO+2YKZZQMbmjTqRI3Qchu8Hig/Q9vgkHpI3alNjr7M+a2St5pw5w5F6NL5/Q=="],
|
||||
|
|
@ -381,6 +385,10 @@
|
|||
|
||||
"@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.31", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw=="],
|
||||
|
||||
"@langchain/core": ["@langchain/core@1.1.27", "", { "dependencies": { "@cfworker/json-schema": "^4.0.2", "ansi-styles": "^5.0.0", "camelcase": "6", "decamelize": "1.2.0", "js-tiktoken": "^1.0.12", "langsmith": ">=0.5.0 <1.0.0", "mustache": "^4.2.0", "p-queue": "^6.6.2", "uuid": "^10.0.0", "zod": "^3.25.76 || ^4" } }, "sha512-YVtEz3nqCh8WxtdVXUICmt2BR2An+mn4YRJUBwcHX47Yrh2VwxpO0l97B2N/sNi658m65HnGyz2/hAjF3fzc1w=="],
|
||||
|
||||
"@langchain/textsplitters": ["@langchain/textsplitters@1.0.1", "", { "dependencies": { "js-tiktoken": "^1.0.12" }, "peerDependencies": { "@langchain/core": "^1.0.0" } }, "sha512-rheJlB01iVtrOUzttscutRgLybPH9qR79EyzBEbf1u97ljWyuxQfCwIWK+SjoQTM9O8M7GGLLRBSYE26Jmcoww=="],
|
||||
|
||||
"@mermaid-js/parser": ["@mermaid-js/parser@0.6.3", "", { "dependencies": { "langium": "3.3.1" } }, "sha512-lnjOhe7zyHjc+If7yT4zoedx2vo4sHaTmtkl1+or8BRTnCtDmcTpAjpzDSfCZrshM5bCoz0GyidzadJAH1xobA=="],
|
||||
|
||||
"@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.26.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-Y5RmPncpiDtTXDbLKswIJzTqu2hyBKxTNsgKqKclDbhIgg1wgtf1fRuvxgTnRfcnxtvvgbIEcqUOzZrJ6iSReg=="],
|
||||
|
|
@ -781,6 +789,8 @@
|
|||
|
||||
"@types/use-sync-external-store": ["@types/use-sync-external-store@0.0.6", "", {}, "sha512-zFDAD+tlpf2r4asuHEj0XH6pY6i0g5NeAHPn+15wk3BV6JA69eERFXC1gyGThDkVa1zCyKr5jox1+2LbV/AMLg=="],
|
||||
|
||||
"@types/uuid": ["@types/uuid@10.0.0", "", {}, "sha512-7gqG38EyHgyP1S+7+xomFtL+ZNHcKv6DwNaCZmJmo1vgMugyF3TCnXVg4t1uk89mLNwnLtnY3TpOpCOyp1/xHQ=="],
|
||||
|
||||
"@types/validate-npm-package-name": ["@types/validate-npm-package-name@4.0.2", "", {}, "sha512-lrpDziQipxCEeK5kWxvljWYhUvOiB2A9izZd9B2AFarYAkqZshb4lPbRs7zKEic6eGtH8V/2qJW+dPp9OtF6bw=="],
|
||||
|
||||
"@typescript-eslint/eslint-plugin": ["@typescript-eslint/eslint-plugin@8.55.0", "", { "dependencies": { "@eslint-community/regexpp": "^4.12.2", "@typescript-eslint/scope-manager": "8.55.0", "@typescript-eslint/type-utils": "8.55.0", "@typescript-eslint/utils": "8.55.0", "@typescript-eslint/visitor-keys": "8.55.0", "ignore": "^7.0.5", "natural-compare": "^1.4.0", "ts-api-utils": "^2.4.0" }, "peerDependencies": { "@typescript-eslint/parser": "^8.55.0", "eslint": "^8.57.0 || ^9.0.0", "typescript": ">=4.8.4 <6.0.0" } }, "sha512-1y/MVSz0NglV1ijHC8OT49mPJ4qhPYjiK08YUQVbIOyu+5k862LKUHFkpKHWu//zmr7hDR2rhwUm6gnCGNmGBQ=="],
|
||||
|
|
@ -827,7 +837,7 @@
|
|||
|
||||
"ansi-regex": ["ansi-regex@6.2.2", "", {}, "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg=="],
|
||||
|
||||
"ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
|
||||
"ansi-styles": ["ansi-styles@5.2.0", "", {}, "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA=="],
|
||||
|
||||
"ansis": ["ansis@4.2.0", "", {}, "sha512-HqZ5rWlFjGiV0tDm3UxxgNRqsOTniqoKZu0pIAfh7TZQMGuZK+hH0drySty0si0QXj1ieop4+SkSfPZBPPkHig=="],
|
||||
|
||||
|
|
@ -869,6 +879,8 @@
|
|||
|
||||
"callsites": ["callsites@3.1.0", "", {}, "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ=="],
|
||||
|
||||
"camelcase": ["camelcase@6.3.0", "", {}, "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA=="],
|
||||
|
||||
"caniuse-lite": ["caniuse-lite@1.0.30001769", "", {}, "sha512-BCfFL1sHijQlBGWBMuJyhZUhzo7wer5sVj9hqekB/7xn0Ypy+pER/edCYQm4exbXj4WiySGp40P8UuTh6w1srg=="],
|
||||
|
||||
"canvas-confetti": ["canvas-confetti@1.9.4", "", {}, "sha512-yxQbJkAVrFXWNbTUjPqjF7G+g6pDotOUHGbkZq2NELZUMDpiJ85rIEazVb8GTaAptNW2miJAXbs1BtioA251Pw=="],
|
||||
|
|
@ -925,6 +937,8 @@
|
|||
|
||||
"confbox": ["confbox@0.1.8", "", {}, "sha512-RMtmw0iFkeR4YV+fUOSucriAQNb9g8zFR52MWCtl+cCZOFRNL6zeB395vPzFhEjjn4fMxXudmELnl/KF/WrK6w=="],
|
||||
|
||||
"console-table-printer": ["console-table-printer@2.15.0", "", { "dependencies": { "simple-wcswidth": "^1.1.2" } }, "sha512-SrhBq4hYVjLCkBVOWaTzceJalvn5K1Zq5aQA6wXC/cYjI3frKWNPEMK3sZsJfNNQApvCQmgBcc13ZKmFj8qExw=="],
|
||||
|
||||
"content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
|
||||
|
||||
"content-type": ["content-type@1.0.5", "", {}, "sha512-nTjqfcBFEipKdXCv4YDQWCfmcLZKm81ldF0pAopTvyrFGVbcR6P/VAAd5G7N+0tTr8QqiU0tFadD6FK4NtJwOA=="],
|
||||
|
|
@ -1033,6 +1047,8 @@
|
|||
|
||||
"debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
|
||||
|
||||
"decamelize": ["decamelize@1.2.0", "", {}, "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA=="],
|
||||
|
||||
"decimal.js-light": ["decimal.js-light@2.5.1", "", {}, "sha512-qIMFpTMZmny+MMIitAB6D7iVPEorVw6YQRWkvarTkT4tBeSLLiHzcwj6q0MmYSFCiVpiqPJTJEYIrpcPzVEIvg=="],
|
||||
|
||||
"decode-named-character-reference": ["decode-named-character-reference@1.3.0", "", { "dependencies": { "character-entities": "^2.0.0" } }, "sha512-GtpQYB283KrPp6nRw50q3U9/VfOutZOe103qlN7BPP6Ad27xYnOIWv4lPzo8HCAL+mMZofJ9KEy30fq6MfaK6Q=="],
|
||||
|
|
@ -1353,6 +1369,8 @@
|
|||
|
||||
"jose": ["jose@6.1.3", "", {}, "sha512-0TpaTfihd4QMNwrz/ob2Bp7X04yuxJkjRGi4aKmOqwhov54i6u79oCv7T+C7lo70MKH6BesI3vscD1yb/yzKXQ=="],
|
||||
|
||||
"js-tiktoken": ["js-tiktoken@1.0.21", "", { "dependencies": { "base64-js": "^1.5.1" } }, "sha512-biOj/6M5qdgx5TKjDnFT1ymSpM5tbd3ylwDtrQvFQSu0Z7bBYko2dF+W/aUkXUPuk6IVpRxk/3Q2sHOzGlS36g=="],
|
||||
|
||||
"js-tokens": ["js-tokens@4.0.0", "", {}, "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="],
|
||||
|
||||
"js-yaml": ["js-yaml@4.1.1", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA=="],
|
||||
|
|
@ -1385,6 +1403,8 @@
|
|||
|
||||
"langium": ["langium@3.3.1", "", { "dependencies": { "chevrotain": "~11.0.3", "chevrotain-allstar": "~0.3.0", "vscode-languageserver": "~9.0.1", "vscode-languageserver-textdocument": "~1.0.11", "vscode-uri": "~3.0.8" } }, "sha512-QJv/h939gDpvT+9SiLVlY7tZC3xB2qK57v0J04Sh9wpMb6MP1q8gB21L3WIo8T5P1MSMg3Ep14L7KkDCFG3y4w=="],
|
||||
|
||||
"langsmith": ["langsmith@0.5.6", "", { "dependencies": { "@types/uuid": "^10.0.0", "chalk": "^5.6.2", "console-table-printer": "^2.12.1", "p-queue": "^6.6.2", "semver": "^7.6.3", "uuid": "^10.0.0" }, "peerDependencies": { "@opentelemetry/api": "*", "@opentelemetry/exporter-trace-otlp-proto": "*", "@opentelemetry/sdk-trace-base": "*", "openai": "*" }, "optionalPeers": ["@opentelemetry/api", "@opentelemetry/exporter-trace-otlp-proto", "@opentelemetry/sdk-trace-base", "openai"] }, "sha512-T/RA2l2MsTYX0z1aW8rQ2hBQZEOuXV2v/6tkfG6R5EotJTKMpw1dERCbvP8ezOP8otyWfnNlQA88ZnMRsQ7CHA=="],
|
||||
|
||||
"layout-base": ["layout-base@1.0.2", "", {}, "sha512-8h2oVEZNktL4BH2JCOI90iD1yXwL6iNW7KcCKT2QZgQJR2vbqDsldCTPRU9NifTCqHZci57XvQQ15YTu+sTYPg=="],
|
||||
|
||||
"levn": ["levn@0.4.1", "", { "dependencies": { "prelude-ls": "^1.2.1", "type-check": "~0.4.0" } }, "sha512-+bT2uH4E5LGE7h/n3evcS/sQlJXCpIp6ym8OWJ5eV6+67Dsql/LaaT7qJBAt2rzfoa/5QBGBhxDix1dMt2kQKQ=="],
|
||||
|
|
@ -1575,6 +1595,8 @@
|
|||
|
||||
"msw": ["msw@2.12.10", "", { "dependencies": { "@inquirer/confirm": "^5.0.0", "@mswjs/interceptors": "^0.41.2", "@open-draft/deferred-promise": "^2.2.0", "@types/statuses": "^2.0.6", "cookie": "^1.0.2", "graphql": "^16.12.0", "headers-polyfill": "^4.0.2", "is-node-process": "^1.2.0", "outvariant": "^1.4.3", "path-to-regexp": "^6.3.0", "picocolors": "^1.1.1", "rettime": "^0.10.1", "statuses": "^2.0.2", "strict-event-emitter": "^0.5.1", "tough-cookie": "^6.0.0", "type-fest": "^5.2.0", "until-async": "^3.0.2", "yargs": "^17.7.2" }, "peerDependencies": { "typescript": ">= 4.8.x" }, "optionalPeers": ["typescript"], "bin": { "msw": "cli/index.js" } }, "sha512-G3VUymSE0/iegFnuipujpwyTM2GuZAKXNeerUSrG2+Eg391wW63xFs5ixWsK9MWzr1AGoSkYGmyAzNgbR3+urw=="],
|
||||
|
||||
"mustache": ["mustache@4.2.0", "", { "bin": { "mustache": "bin/mustache" } }, "sha512-71ippSywq5Yb7/tVYyGbkBggbU8H3u5Rz56fH60jGFgr8uHwxs+aSKeqmluIVzM0m0kB7xQjKS6qPfd0b2ZoqQ=="],
|
||||
|
||||
"mute-stream": ["mute-stream@2.0.0", "", {}, "sha512-WWdIxpyjEn+FhQJQQv9aQAYlHoNVdzIzUySNV1gHUPDSdZJ3yZn7pAAbQcV7B56Mvu881q9FZV+0Vx2xC44VWA=="],
|
||||
|
||||
"nanoid": ["nanoid@5.1.6", "", { "bin": { "nanoid": "bin/nanoid.js" } }, "sha512-c7+7RQ+dMB5dPwwCp4ee1/iV/q2P6aK1mTZcfr1BTuVlyW9hJYiMPybJCcnBlQtuSmTIWNeazm/zqNoZSSElBg=="],
|
||||
|
|
@ -1621,10 +1643,16 @@
|
|||
|
||||
"outvariant": ["outvariant@1.4.3", "", {}, "sha512-+Sl2UErvtsoajRDKCE5/dBz4DIvHXQQnAxtQTF04OJxY0+DyZXSo5P5Bb7XYWOh81syohlYL24hbDwxedPUJCA=="],
|
||||
|
||||
"p-finally": ["p-finally@1.0.0", "", {}, "sha512-LICb2p9CB7FS+0eR1oqWnHhp0FljGLZCWBE9aix0Uye9W8LTQPwMTYVGWQWIw9RdQiDg4+epXQODwIYJtSJaow=="],
|
||||
|
||||
"p-limit": ["p-limit@3.1.0", "", { "dependencies": { "yocto-queue": "^0.1.0" } }, "sha512-TYOanM3wGwNGsZN2cVTYPArw454xnXj5qmWF1bEoAc4+cU/ol7GVh7odevjp1FNHduHc3KZMcFduxU5Xc6uJRQ=="],
|
||||
|
||||
"p-locate": ["p-locate@5.0.0", "", { "dependencies": { "p-limit": "^3.0.2" } }, "sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw=="],
|
||||
|
||||
"p-queue": ["p-queue@6.6.2", "", { "dependencies": { "eventemitter3": "^4.0.4", "p-timeout": "^3.2.0" } }, "sha512-RwFpb72c/BhQLEXIZ5K2e+AhgNVmIejGlTgiB9MzZ0e93GRvqZ7uSi0dvRF7/XIXDeNkra2fNHBxTyPDGySpjQ=="],
|
||||
|
||||
"p-timeout": ["p-timeout@3.2.0", "", { "dependencies": { "p-finally": "^1.0.0" } }, "sha512-rhIwUycgwwKcP9yTOOFK/AKsAopjjCakVqLHePO3CC6Mir1Z99xT+R63jZxAT5lFZLa2inS5h+ZS2GvR99/FBg=="],
|
||||
|
||||
"package-manager-detector": ["package-manager-detector@1.6.0", "", {}, "sha512-61A5ThoTiDG/C8s8UMZwSorAGwMJ0ERVGj2OjoW5pAalsNOg15+iQiPzrLJ4jhZ1HJzmC2PIHT2oEiH3R5fzNA=="],
|
||||
|
||||
"pako": ["pako@1.0.11", "", {}, "sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw=="],
|
||||
|
|
@ -1831,6 +1859,8 @@
|
|||
|
||||
"signal-exit": ["signal-exit@4.1.0", "", {}, "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw=="],
|
||||
|
||||
"simple-wcswidth": ["simple-wcswidth@1.1.2", "", {}, "sha512-j7piyCjAeTDSjzTSQ7DokZtMNwNlEAyxqSZeCS+CXH7fJ4jx3FuJ/mTW3mE+6JLs4VJBbcll0Kjn+KXI5t21Iw=="],
|
||||
|
||||
"sisteransi": ["sisteransi@1.0.5", "", {}, "sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg=="],
|
||||
|
||||
"sonner": ["sonner@2.0.7", "", { "peerDependencies": { "react": "^18.0.0 || ^19.0.0 || ^19.0.0-rc", "react-dom": "^18.0.0 || ^19.0.0 || ^19.0.0-rc" } }, "sha512-W6ZN4p58k8aDKA4XPcx2hpIQXBRAgyiWVkYhT7CvK6D3iAu7xjvVyhQHg2/iaKJZ1XVJ4r7XuwGL+WGEK37i9w=="],
|
||||
|
|
@ -1985,7 +2015,7 @@
|
|||
|
||||
"util-deprecate": ["util-deprecate@1.0.2", "", {}, "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw=="],
|
||||
|
||||
"uuid": ["uuid@11.1.0", "", { "bin": { "uuid": "dist/esm/bin/uuid" } }, "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A=="],
|
||||
"uuid": ["uuid@10.0.0", "", { "bin": { "uuid": "dist/bin/uuid" } }, "sha512-8XkAphELsDnEGrDxUOHB3RGvXz6TeuYSGEZBOjtTtPm2lwhGBjLgOzLHB63IUWfBpNucQjND6d3AOudO+H3RWQ=="],
|
||||
|
||||
"validate-npm-package-name": ["validate-npm-package-name@7.0.2", "", {}, "sha512-hVDIBwsRruT73PbK7uP5ebUt+ezEtCmzZz3F59BSr2F6OVFnJ/6h8liuvdLrQ88Xmnk6/+xGGuq+pG9WwTuy3A=="],
|
||||
|
||||
|
|
@ -2249,6 +2279,8 @@
|
|||
|
||||
"ajv-formats/ajv": ["ajv@8.17.1", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-B/gBuNg5SiMTrPkC+A2+cW0RszwxYmn6VYxB/inlBStS5nx6xHIt/ehKRhIMhqusl7a8LjQoZnjCs5vhwxOQ1g=="],
|
||||
|
||||
"chalk/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
|
||||
|
||||
"chevrotain/lodash-es": ["lodash-es@4.17.21", "", {}, "sha512-mKnC+QJ9pWVzv+C4/U3rRsHapFfHvQFoFB92e52xeyGMcX6/OlIl78je1u8vePzYZSkkogMPJ2yjxxsb89cxyw=="],
|
||||
|
||||
"cliui/strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
|
||||
|
|
@ -2271,6 +2303,10 @@
|
|||
|
||||
"js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
|
||||
|
||||
"langsmith/chalk": ["chalk@5.6.2", "", {}, "sha512-7NzBL0rN6fMUW+f7A6Io4h40qQlG+xGmtMxfbnH/K7TAtt8JQWVQK+6g0UXKMeVJoyV5EkkNsErQ8pVD3bLHbA=="],
|
||||
|
||||
"langsmith/semver": ["semver@7.7.4", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-vFKC2IEtQnVhpT78h1Yp8wzwrf8CM+MzKMHGJZfBtzhZNycRFnXsHk6E5TxIkkMsgNS7mdX3AGB7x2QM2di4lA=="],
|
||||
|
||||
"log-symbols/chalk": ["chalk@5.6.2", "", {}, "sha512-7NzBL0rN6fMUW+f7A6Io4h40qQlG+xGmtMxfbnH/K7TAtt8JQWVQK+6g0UXKMeVJoyV5EkkNsErQ8pVD3bLHbA=="],
|
||||
|
||||
"log-symbols/is-unicode-supported": ["is-unicode-supported@1.3.0", "", {}, "sha512-43r2mRvz+8JRIKnWJ+3j8JtjRKZ6GmjzfaE/qiBJnikNnYv/6bagRJ1kUhNk8R5EX/GkobD+r+sfxCPJsiKBLQ=="],
|
||||
|
|
@ -2279,6 +2315,8 @@
|
|||
|
||||
"mermaid/marked": ["marked@16.4.2", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-TI3V8YYWvkVf3KJe1dRkpnjs68JUPyEa5vjKrp1XEEJUAOaQc+Qj+L1qWbPd0SJuAdQkFU0h73sXXqwDYxsiDA=="],
|
||||
|
||||
"mermaid/uuid": ["uuid@11.1.0", "", { "bin": { "uuid": "dist/esm/bin/uuid" } }, "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A=="],
|
||||
|
||||
"micromatch/picomatch": ["picomatch@2.3.1", "", {}, "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA=="],
|
||||
|
||||
"motion/framer-motion": ["framer-motion@12.34.0", "", { "dependencies": { "motion-dom": "^12.34.0", "motion-utils": "^12.29.2", "tslib": "^2.4.0" }, "peerDependencies": { "@emotion/is-prop-valid": "*", "react": "^18.0.0 || ^19.0.0", "react-dom": "^18.0.0 || ^19.0.0" }, "optionalPeers": ["@emotion/is-prop-valid", "react", "react-dom"] }, "sha512-+/H49owhzkzQyxtn7nZeF4kdH++I2FWrESQ184Zbcw5cEqNHYkE5yxWxcTLSj5lNx3NWdbIRy5FHqUvetD8FWg=="],
|
||||
|
|
@ -2291,6 +2329,8 @@
|
|||
|
||||
"ora/string-width": ["string-width@7.2.0", "", { "dependencies": { "emoji-regex": "^10.3.0", "get-east-asian-width": "^1.0.0", "strip-ansi": "^7.1.0" } }, "sha512-tsaTIkKW9b4N+AEj+SVA+WhJzV7/zMhcSu78mLKWSk7cXMOSHsBKFWUs0fWwq8QyK3MgJBQRX6Gbi4kYbdvGkQ=="],
|
||||
|
||||
"p-queue/eventemitter3": ["eventemitter3@4.0.7", "", {}, "sha512-8guHBZCwKnFhYdHr2ysuRWErTwhoN2X8XELRlrRwpmfeY2jjuUN4taQMsULKUVo1K4DvZl+0pgfyoysHxvmvEw=="],
|
||||
|
||||
"parse-entities/@types/unist": ["@types/unist@2.0.11", "", {}, "sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA=="],
|
||||
|
||||
"postcss/nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
|
||||
|
|
@ -2319,6 +2359,8 @@
|
|||
|
||||
"string-width/strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
|
||||
|
||||
"wrap-ansi/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
|
||||
|
||||
"wrap-ansi/strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
|
||||
|
||||
"@dotenvx/dotenvx/execa/get-stream": ["get-stream@6.0.1", "", {}, "sha512-ts6Wi+2j3jQjqi70w5AlN8DFnkSwC+MqmxEzdEALB2qXZYV3X/b1CTfgPLGJNMeAWxdPfU8FO1ms3NUfaHCPYg=="],
|
||||
|
|
@ -2407,6 +2449,8 @@
|
|||
|
||||
"cliui/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
|
||||
|
||||
"cliui/wrap-ansi/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
|
||||
|
||||
"cytoscape-fcose/cose-base/layout-base": ["layout-base@2.0.1", "", {}, "sha512-dp3s92+uNI1hWIpPGH3jK2kxE2lMjdXdr+DH8ynZHpd6PUlH6x6cbuXnoMmiNumznqaNO31xu9e79F0uuZ0JFg=="],
|
||||
|
||||
"d3-sankey/d3-array/internmap": ["internmap@1.0.1", "", {}, "sha512-lDB5YccMydFBtasVtxnZ3MRBHuaoE8GKsppq+EchKL2U4nK/DmEpPHNH8MZe5HkMtpSiTSOZwfN0tzYjO/lJEw=="],
|
||||
|
|
|
|||
|
|
@ -25,6 +25,8 @@
|
|||
"@hugeicons/core-free-icons": "^3.1.1",
|
||||
"@hugeicons/react": "^1.1.5",
|
||||
"@huggingface/hub": "^2.9.0",
|
||||
"@langchain/core": "^1.1.27",
|
||||
"@langchain/textsplitters": "^1.0.1",
|
||||
"@radix-ui/react-checkbox": "^1.3.3",
|
||||
"@radix-ui/react-label": "^2.1.8",
|
||||
"@radix-ui/react-select": "^2.2.6",
|
||||
|
|
|
|||
|
|
@ -33,6 +33,7 @@ import {
|
|||
TabsList,
|
||||
TabsTrigger,
|
||||
} from "@/components/ui/tabs";
|
||||
import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
|
||||
import mammoth from "mammoth";
|
||||
import { type ReactElement, useEffect, useMemo, useState } from "react";
|
||||
import { extractText, getDocumentProxy } from "unpdf";
|
||||
|
|
@ -60,6 +61,10 @@ const UNSTRUCTURED_ACCEPT = ".txt,.pdf,.docx";
|
|||
const MAX_UPLOAD_BYTES = 50 * 1024 * 1024;
|
||||
const CHUNK_SIZE = 1200;
|
||||
const CHUNK_OVERLAP = 200;
|
||||
const UNSTRUCTURED_SPLITTER = new RecursiveCharacterTextSplitter({
|
||||
chunkSize: CHUNK_SIZE,
|
||||
chunkOverlap: CHUNK_OVERLAP,
|
||||
});
|
||||
|
||||
type SeedDialogProps = {
|
||||
config: SeedConfig;
|
||||
|
|
@ -84,20 +89,12 @@ function stringifyCell(value: unknown): string {
|
|||
}
|
||||
}
|
||||
|
||||
function chunkText(input: string): string[] {
|
||||
async function chunkText(input: string): Promise<string[]> {
|
||||
const text = input.replace(/\r\n/g, "\n").replace(/\n{3,}/g, "\n\n").trim();
|
||||
if (!text) return [];
|
||||
|
||||
const chunks: string[] = [];
|
||||
let cursor = 0;
|
||||
const overlap = Math.max(0, Math.min(CHUNK_OVERLAP, CHUNK_SIZE - 1));
|
||||
while (cursor < text.length) {
|
||||
const end = Math.min(cursor + CHUNK_SIZE, text.length);
|
||||
chunks.push(text.slice(cursor, end).trim());
|
||||
if (end >= text.length) break;
|
||||
cursor = Math.max(0, end - overlap);
|
||||
}
|
||||
return chunks.filter(Boolean);
|
||||
const chunks = await UNSTRUCTURED_SPLITTER.splitText(text);
|
||||
return chunks.map((chunk) => chunk.trim()).filter(Boolean);
|
||||
}
|
||||
|
||||
async function fileToBase64Payload(file: File): Promise<string> {
|
||||
|
|
@ -218,7 +215,7 @@ export function SeedDialog({ config, onUpdate }: SeedDialogProps): ReactElement
|
|||
}
|
||||
|
||||
const text = await extractUnstructuredText(unstructuredFile);
|
||||
const chunks = chunkText(text);
|
||||
const chunks = await chunkText(text);
|
||||
if (chunks.length === 0) {
|
||||
throw new Error("No text found in file.");
|
||||
}
|
||||
|
|
|
|||
|
|
@ -300,12 +300,12 @@ export const useRecipeStudioStore = create<RecipeStudioState>((set, get) => ({
|
|||
if (!existing) {
|
||||
return buildAddedNodeState(state, "seed", type);
|
||||
}
|
||||
const nextSourceType: SeedSourceType =
|
||||
type === "seed_local"
|
||||
? "local"
|
||||
: type === "seed_unstructured"
|
||||
? "unstructured"
|
||||
: "hf";
|
||||
let nextSourceType: SeedSourceType = "hf";
|
||||
if (type === "seed_local") {
|
||||
nextSourceType = "local";
|
||||
} else if (type === "seed_unstructured") {
|
||||
nextSourceType = "unstructured";
|
||||
}
|
||||
|
||||
const nextConfig = {
|
||||
...existing,
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@ import type {
|
|||
LlmToolConfig,
|
||||
NodeConfig,
|
||||
RecipeProcessorConfig,
|
||||
SeedSourceType,
|
||||
} from "../../types";
|
||||
import { buildEdges } from "./edges";
|
||||
import { isRecord, parseJson, readString } from "./helpers";
|
||||
|
|
@ -29,6 +30,7 @@ type RecipeInput = {
|
|||
type UiInput = {
|
||||
nodes?: unknown;
|
||||
edges?: unknown;
|
||||
seed_source_type?: unknown;
|
||||
};
|
||||
|
||||
function parseProcessors(input: unknown): RecipeProcessorConfig[] {
|
||||
|
|
@ -219,11 +221,18 @@ export function importRecipePayload(input: string): ImportResult {
|
|||
const nameToId = new Map<string, string>();
|
||||
|
||||
let nextId = 1;
|
||||
const uiSeedSourceTypeRaw = readString(ui?.seed_source_type);
|
||||
const uiSeedSourceType: SeedSourceType | undefined =
|
||||
uiSeedSourceTypeRaw === "hf" ||
|
||||
uiSeedSourceTypeRaw === "local" ||
|
||||
uiSeedSourceTypeRaw === "unstructured"
|
||||
? uiSeedSourceTypeRaw
|
||||
: undefined;
|
||||
|
||||
if (recipe.seed_config) {
|
||||
const id = `n${nextId}`;
|
||||
nextId += 1;
|
||||
const seedConfig = parseSeedConfig(recipe.seed_config, id);
|
||||
const seedConfig = parseSeedConfig(recipe.seed_config, id, uiSeedSourceType);
|
||||
if (seedConfig) {
|
||||
configs.push(seedConfig);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -65,7 +65,7 @@ function parseSeedSettings(seedConfigRaw: unknown): Partial<SeedConfig> {
|
|||
let hf_endpoint = "https://huggingface.co";
|
||||
let hf_repo_id = "";
|
||||
let local_file_name = "";
|
||||
let unstructured_file_name = "";
|
||||
const unstructured_file_name = "";
|
||||
const sourceRaw = seedConfigRaw.source;
|
||||
if (isRecord(sourceRaw)) {
|
||||
const seedType = readString(sourceRaw.seed_type);
|
||||
|
|
@ -127,12 +127,23 @@ function parseSeedSettings(seedConfigRaw: unknown): Partial<SeedConfig> {
|
|||
export function parseSeedConfig(
|
||||
seedConfigRaw: unknown,
|
||||
id: string,
|
||||
preferredSourceType?: SeedSourceType,
|
||||
): SeedConfig | null {
|
||||
if (!seedConfigRaw) {
|
||||
return null;
|
||||
}
|
||||
const parsed = parseSeedSettings(seedConfigRaw);
|
||||
let sourceType: SeedSourceType = "hf";
|
||||
if (parsed.seed_source_type === "hf") {
|
||||
sourceType = "hf";
|
||||
} else if (preferredSourceType) {
|
||||
sourceType = preferredSourceType;
|
||||
} else if (parsed.seed_source_type) {
|
||||
sourceType = parsed.seed_source_type;
|
||||
}
|
||||
return {
|
||||
...makeDefaultSeedConfig(id),
|
||||
...parseSeedSettings(seedConfigRaw), // payload-only fields override ui defaults
|
||||
...parsed, // payload-only fields override ui defaults
|
||||
seed_source_type: sourceType,
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -241,6 +241,7 @@ export function buildRecipePayload(
|
|||
ui: {
|
||||
nodes: uiNodes,
|
||||
edges: uiEdges,
|
||||
...(firstSeed && { seed_source_type: firstSeed.seed_source_type }),
|
||||
},
|
||||
},
|
||||
};
|
||||
|
|
|
|||
|
|
@ -30,6 +30,8 @@ export type RecipePayload = {
|
|||
ui: {
|
||||
nodes: { id: string; x: number; y: number }[];
|
||||
edges: { from: string; to: string; type?: string }[];
|
||||
// ui-only, used to preserve seed block mode across imports/refresh
|
||||
seed_source_type?: "hf" | "local" | "unstructured";
|
||||
};
|
||||
};
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue