deepresearch-flow 0.5.1__py3-none-any.whl → 0.6.1__py3-none-any.whl

{deepresearch_flow-0.5.1.dist-info → deepresearch_flow-0.6.1.dist-info}/RECORD

@@ -2,54 +2,62 @@ deepresearch_flow/__init__.py,sha256=rjP9ES4zJCfEN_MCDYAYPL1mNJZGjojdmbRwnZ9FlEk
 deepresearch_flow/__main__.py,sha256=Ceo0rMTOhHhwFPD-HyDDagenNsmWEzPmsdYLI7kwKVA,115
 deepresearch_flow/cli.py,sha256=t4oowCNWldL0DrVJ4d0UlRkuGU2qHej_G0mAc_quteQ,455
 deepresearch_flow/paper/__init__.py,sha256=sunaOkcgAJBrfmcaJTumcWbPGVUSGWvOv2a2Yidzy0A,43
-deepresearch_flow/paper/cli.py,sha256=4UY3KHi6BUGztL1vB4w0cCMiIAo9KNxrfQn1GBHt6fA,11153
-deepresearch_flow/paper/config.py,sha256=totVBGzouh0KS6mhRNPneXZYPuuw0SHiOGdO3r6HSfc,9289
-deepresearch_flow/paper/db.py,sha256=-9Wl-ivIu0N8bC6lFGxxBKKQewD8aay7Aq-ynfhEqJg,43002
-deepresearch_flow/paper/db_ops.py,sha256=Nwbou8y3jMNKMcvDSJfmi5NYQwEtoHk1E_7TbwDoYX8,70501
-deepresearch_flow/paper/extract.py,sha256=ID1dd2r6LTB0kRF4qBSH6bGtBGv0znw--g_mXYBcoeU,32314
+deepresearch_flow/paper/cli.py,sha256=68d-yccScU0yL6d7eqZVdudPO6i_in8F4v-hKDWILMo,13647
+deepresearch_flow/paper/config.py,sha256=V7z4ApPXCV1acSl2FU3nZGq6nt8uisMhm0GtOq5zzmg,12021
+deepresearch_flow/paper/db.py,sha256=Bxhrd8NCaPZ9Ijtp1uiOplwh2Uy0n2Dyn1bO0d4A9bE,91780
+deepresearch_flow/paper/db_ops.py,sha256=cb64jn2ax39i3tCS-0DYmlsJdGX3uBS2u5ncUIbUBic,73980
+deepresearch_flow/paper/extract.py,sha256=78ASAyNLfCl1AsAk2o_v1vskZCNZuayaCHgr0S4V2Vs,87632
 deepresearch_flow/paper/llm.py,sha256=mHfs5IkT3Q6BOh46MDlfUmgVTX24WRf0IKKoOnN8nV8,4007
 deepresearch_flow/paper/prompts.py,sha256=mV7cEXw8pwukBUE4Trah0SjEPSSDgg5-RGaNaUdo4EU,519
 deepresearch_flow/paper/render.py,sha256=KeccrRGf1_sxoaiT6SUDkFRj9sStReoEwNvlw1ir7qw,2181
 deepresearch_flow/paper/schema.py,sha256=tQEVbj4R8NqNGBW6VYwW-xf5QJgV9qthrbZB-EmZTKA,1931
-deepresearch_flow/paper/template_registry.py,sha256=OSJOLAHFOtjsGR7sNXYstL8Z6VdY5g-KvBhNMgVUNXw,7387
+deepresearch_flow/paper/template_registry.py,sha256=r0-uVIeeVcPKMD9TpIZ5kAi4CvMrJQoJTHBSEamA8Ko,7427
 deepresearch_flow/paper/utils.py,sha256=Lbr4OLiTtGJ8qX3AXOZHJdLVPVqdVLewClQKT_2XAQA,3788
 deepresearch_flow/paper/prompt_templates/__init__.py,sha256=b72Jin1J2Q7KS3635Te3YZm1ZXhuMIPzDVUH172Rphc,33
-deepresearch_flow/paper/prompt_templates/deep_read_phi_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
-deepresearch_flow/paper/prompt_templates/deep_read_phi_user.j2,sha256=UAobEe25nIyr0f7jAfL3ca5qZzHHJHKE3O-NixwBibI,17581
-deepresearch_flow/paper/prompt_templates/deep_read_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
-deepresearch_flow/paper/prompt_templates/deep_read_user.j2,sha256=VS_6ZkhN_h3-ur7tA4sosdPttjCg9ZwlhAn1LR4tsag,4068
-deepresearch_flow/paper/prompt_templates/eight_questions_phi_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
-deepresearch_flow/paper/prompt_templates/eight_questions_phi_user.j2,sha256=9q6zSLZO2OhRNvOg0tCFFYH6avUyGAf3yW6wsnRyOvQ,7866
-deepresearch_flow/paper/prompt_templates/eight_questions_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
-deepresearch_flow/paper/prompt_templates/eight_questions_user.j2,sha256=vyfMstnXAb5zLsxcqyYxTt5OWjpmPVoqaV-dIJshcrw,1339
-deepresearch_flow/paper/prompt_templates/simple_phi_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
+deepresearch_flow/paper/prompt_templates/deep_read_phi_system.j2,sha256=_KxtVHV54VElOPm9l6P9rJmN7Sd6-JL6SDiQDd2QQCM,528
+deepresearch_flow/paper/prompt_templates/deep_read_phi_user.j2,sha256=kI8Rsp03Fy5XBkqh8qYtsTGa6elnUNKc_Epfx42puNk,17954
+deepresearch_flow/paper/prompt_templates/deep_read_system.j2,sha256=_KxtVHV54VElOPm9l6P9rJmN7Sd6-JL6SDiQDd2QQCM,528
+deepresearch_flow/paper/prompt_templates/deep_read_user.j2,sha256=q9PkrO32tepg7km8mqACGWFW2mGTaYHUlVsLfEVB87g,12785
+deepresearch_flow/paper/prompt_templates/eight_questions_phi_system.j2,sha256=eZqgnNACpCNGxqZDo_JDq9m0VNc7p0qHe3fzmYzOv3s,466
+deepresearch_flow/paper/prompt_templates/eight_questions_phi_user.j2,sha256=sujB0jNicF9tswFzIoo97KNteY9QLBuE7oeVbnak8PM,8110
+deepresearch_flow/paper/prompt_templates/eight_questions_system.j2,sha256=_KxtVHV54VElOPm9l6P9rJmN7Sd6-JL6SDiQDd2QQCM,528
+deepresearch_flow/paper/prompt_templates/eight_questions_user.j2,sha256=eXSN_Cyla29m2wp6loQH4g6RU6aDxqskK9ICDSyyDho,1634
+deepresearch_flow/paper/prompt_templates/simple_phi_system.j2,sha256=_KxtVHV54VElOPm9l6P9rJmN7Sd6-JL6SDiQDd2QQCM,528
 deepresearch_flow/paper/prompt_templates/simple_phi_user.j2,sha256=LL_h0O1wcGLZQtuhTfUUhURjAoJwH8Vrmh3XzeB9bRM,2089
-deepresearch_flow/paper/prompt_templates/simple_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
-deepresearch_flow/paper/prompt_templates/simple_user.j2,sha256=UX2FlsJkRdvbgPZmlCFzB7E2peGKpIjMGqkBfBQ4EHM,774
+deepresearch_flow/paper/prompt_templates/simple_system.j2,sha256=_KxtVHV54VElOPm9l6P9rJmN7Sd6-JL6SDiQDd2QQCM,528
+deepresearch_flow/paper/prompt_templates/simple_user.j2,sha256=f6XvUKwyi1BP6lW2XYDbEeIW4YsA2UmdrA0YdIZD750,840
 deepresearch_flow/paper/prompt_templates/three_pass_system.j2,sha256=WR7fp9nQYmXU5COwAfzly5noXEQEoFrh2Kx4YedvMww,364
 deepresearch_flow/paper/prompt_templates/three_pass_user.j2,sha256=R9OwcS_hmPlSRIv0-63YXqQBux_Uuv6iF7W4xy77nk8,1757
 deepresearch_flow/paper/providers/__init__.py,sha256=OiX-WYHweZ_FCeGS_siSEJndLXfWj2h8I0Am16P7KYQ,32
-deepresearch_flow/paper/providers/azure_openai.py,sha256=8xNaQ_5p8tXWzZ77g7rlwyknvrl6oxMgpzZVzq-4zEM,2206
+deepresearch_flow/paper/providers/azure_openai.py,sha256=bejdKNAr3y5zQt33EbVao9ao3c842T-fWICVDlAy9Go,3530
 deepresearch_flow/paper/providers/base.py,sha256=WrfOVcpXTgxAGLvRogCCc3zXd5O5v4TYeTsSWOe9muM,537
 deepresearch_flow/paper/providers/claude.py,sha256=xFk2T2hSVb--sYBQbrvwykRSbEbEfYcoV9soRPpoTHU,2073
 deepresearch_flow/paper/providers/dashscope.py,sha256=UDg7bQY3EIj3wG2hbl36Bhr_uNjJcn_wPZZ6zSPHDY4,1732
 deepresearch_flow/paper/providers/gemini.py,sha256=x_JegccP4JK0pBj7slz7gVwX-6-ep8v_kl8NglqOUGg,3256
 deepresearch_flow/paper/providers/ollama.py,sha256=j3vZgP6gyxu9n5VF-4v8p3nOCbetzmnlaBjZmvuYKxE,1439
-deepresearch_flow/paper/providers/openai_compatible.py,sha256=eidpcOm5D24e0YU80ECUXcCnWgsMDv7gRXf3vnJlP4M,2077
+deepresearch_flow/paper/providers/openai_compatible.py,sha256=AfNshL08WicAEdC7sO31hQMKqbpopunk0gu3PxOZhG4,3401
 deepresearch_flow/paper/schemas/__init__.py,sha256=NzRW1ugk01AZMkoDOrK-RF-fypYxYKOnyyKDzlHUQ40,29
-deepresearch_flow/paper/schemas/deep_read_phi_schema.json,sha256=_kPHH4RKzfTlYrDW7XgNhBECAAHXlvpNnnX9EP6Wqjk,823
-deepresearch_flow/paper/schemas/deep_read_schema.json,sha256=f9yhsisW_zSxRpjTn1D3-nsmtJMHmGJLLvRGPEmQX0s,1263
-deepresearch_flow/paper/schemas/default_paper_schema.json,sha256=Ncz-XSOJuB5jz1k7jAG7ha819rXPL4UGew06fJHkImM,827
-deepresearch_flow/paper/schemas/eight_questions_schema.json,sha256=3jYQeKvJWduuU_4En-M-s0gEJMOjdjYeu_ENlf8CDyw,931
+deepresearch_flow/paper/schemas/deep_read_phi_schema.json,sha256=i6JA-kJg0BaTeOj_w0AMkS8Uj0gdB5_Y8EPWZb5hg-M,897
+deepresearch_flow/paper/schemas/deep_read_schema.json,sha256=BqQE8T6y_gXt_on75x7MuYJOAcoeRQLw96JfRYvKNYk,1337
+deepresearch_flow/paper/schemas/default_paper_schema.json,sha256=6h_2ayHolJj8JMnFQ6kYNC9diQr-LWuW-ineCAB5OIM,935
+deepresearch_flow/paper/schemas/eight_questions_schema.json,sha256=VFKKpdZkgPdQkYIW5jyrZQ7c2TlQZwB4svVWfoiwxdg,1005
 deepresearch_flow/paper/schemas/three_pass_schema.json,sha256=8aNr4EdRiilxszIRBCC4hRNXrfIOcdnVW4Qhe6Fnh0o,689
+deepresearch_flow/paper/snapshot/__init__.py,sha256=1VLO36xxDB3J5Yoo-HH9vyI-4ev2HcivXN0sNLg8O5k,102
+deepresearch_flow/paper/snapshot/api.py,sha256=WgkOgS7n_2Fx-Bl4KnLrh5nhRJAsWJaPjXu7vX5ubxY,36960
+deepresearch_flow/paper/snapshot/builder.py,sha256=HbRcfNteMoP4RnQ4y2onZCm9XfnIvzXLn_EwsLZsDzY,38692
+deepresearch_flow/paper/snapshot/identity.py,sha256=k9x1EZPFBU1qgxzkTGvwVtDjLgcosmM_udPuvRLl0uI,7748
+deepresearch_flow/paper/snapshot/schema.py,sha256=DcVmAklLYyEeDoVV9jYw7hoMHnHd9Eziivl-LP2busY,8991
+deepresearch_flow/paper/snapshot/text.py,sha256=0RnxLowa6AdirdLsUYym6BhWbjwiP2Qj2oZeA-pjmdE,4368
+deepresearch_flow/paper/snapshot/tests/__init__.py,sha256=G0IowrxHjGUIaqxcw6SvlcLFAtE5ZsleG6ECgd-sIdk,52
+deepresearch_flow/paper/snapshot/tests/test_identity.py,sha256=KDFixAUU9l68KOum7gf1IrD0Oy18dBCSXG7RbJTqflA,4520
 deepresearch_flow/paper/templates/__init__.py,sha256=p8W6kINvrf-T2X6Ow4GMr28syVOorFuMn0pbmieVzAw,35
-deepresearch_flow/paper/templates/deep_read.md.j2,sha256=yYe2IotBpoDnpUE8lR0OaHMzmiH8rDNRQkaaELpuhPA,4637
-deepresearch_flow/paper/templates/deep_read_phi.md.j2,sha256=c9jBJv2L4YLQutYuzYw_6DAgJUtBeQWOphTMp94AjKs,1523
-deepresearch_flow/paper/templates/default_paper.md.j2,sha256=3azu48534QtLtHrCwI1sXtQUSaPfpWBVFOY44s-G63Y,887
-deepresearch_flow/paper/templates/eight_questions.md.j2,sha256=Ecz4CD3nd7jZ4Dg8himZkTwF4WDkk0ILWk8V728uOPI,3038
+deepresearch_flow/paper/templates/deep_read.md.j2,sha256=vwVSPOzMBFIS72ez5XFBaKrDZGz0z32L3VGP6mNk434,4780
+deepresearch_flow/paper/templates/deep_read_phi.md.j2,sha256=6Yz2Kxk0czGDPkZiWX3b87glLYHwDU1afr6CkjS-dh8,1666
+deepresearch_flow/paper/templates/default_paper.md.j2,sha256=dMObS30OpZZ2Np0WHUgA1BBuvsRg6JsOEkeT4NO_NI4,1030
+deepresearch_flow/paper/templates/eight_questions.md.j2,sha256=G0bJCMY4keKraofPLJ7PtS74lMYIoYYX0BMoGwDFXb0,3181
 deepresearch_flow/paper/templates/three_pass.md.j2,sha256=ZRj-NkpZePnqp0gSE8OT1dN5Lr5RW4vdOYdeVejYJW0,1576
 deepresearch_flow/paper/web/__init__.py,sha256=eQBtBjvOYsNEdivHTI0aO286SCG2c86xI02tf-0jz5I,39
-deepresearch_flow/paper/web/app.py,sha256=DxrcwrtwUKLZfjT25_ly1zfnqvgL1A8zDF6W7pCb8BY,7246
+deepresearch_flow/paper/web/app.py,sha256=M1CiMkAc6Mz6Z3L-awytVY-LM-kqLbKHF7wsxNw9HYc,7502
 deepresearch_flow/paper/web/constants.py,sha256=0QZjySqVt2c6PZFoykVoeVgZAXsUahfL4ZVQlfL_qAY,1165
 deepresearch_flow/paper/web/filters.py,sha256=OVMB4GfigP9GPD5dXytHyeLYtnVXEK-QjYfA_k7QbaA,8315
 deepresearch_flow/paper/web/markdown.py,sha256=pwVGy-7kQHsEFo15SmNcQw15-v7lJn_N3VLd827L7uk,26852
@@ -440,24 +448,24 @@ deepresearch_flow/paper/web/templates/detail.html,sha256=NvYDKajgVYrSF9ayVCpMglK
 deepresearch_flow/paper/web/templates/index.html,sha256=qNWwyQWa3QzmHdJbohSe5PJOZS3-KxWjk0RxoQSZiys,6117
 deepresearch_flow/paper/web/templates/stats.html,sha256=bcQBawoZ9KoRkM0NNo9WJBVeN_8O1WU2xNiye-Fugyo,671
 deepresearch_flow/recognize/__init__.py,sha256=yMAqbdCzpdRSiwFhq9j7yx9ZWxqz_Zq3vfYlTLFCWek,33
-deepresearch_flow/recognize/cli.py,sha256=QV0d9XhOdcWcr05427GPSSMheal06WvvmejV7wLVfz8,53460
+deepresearch_flow/recognize/cli.py,sha256=0YMyNfEdQB6Vz7bhaOI3o3tc5ZnoOkHwGQTNKyPjWzg,67312
 deepresearch_flow/recognize/katex_check.js,sha256=jKFLk0Y7y_XR0fBJe2xdfQhAMMuYRXo-pSpWqcEyAH0,735
-deepresearch_flow/recognize/markdown.py,sha256=y-PMJbGqrfWCNBVGanXK1M4OuMP9e1eqh7HDYye5a7Q,8757
-deepresearch_flow/recognize/math.py,sha256=qgI4WRsoWgLaue9OxIq1pcO18wUOlpCNBLKQgicN2hs,22623
-deepresearch_flow/recognize/mermaid.py,sha256=O8uQoEC9mG4mSdTpr-OnmP_vrThaFdUeqt6U00m6O-0,22545
-deepresearch_flow/recognize/organize.py,sha256=nxeWWm7PIp12WvDllYljYNnHqFSlcV7-kInMoHjdblc,5190
+deepresearch_flow/recognize/markdown.py,sha256=8B4cR0n1gC2rXceita25Phi0Lo4uyDweYuXbRB1laH4,9472
+deepresearch_flow/recognize/math.py,sha256=jvTkujqMob4LPuiltoKgss36GaIhCa6hQmnpraqOTiI,24073
+deepresearch_flow/recognize/mermaid.py,sha256=rc5eTwn4i1dKZRua6igFZW08lhqXqqUcijACtCqNS1g,33819
+deepresearch_flow/recognize/organize.py,sha256=KyhcwJ6ckWaZTCyE4M1e5k6ABRHHGWpAF9Re4LB-Sks,5883
 deepresearch_flow/translator/__init__.py,sha256=iaAkufvEELVKNbcs08Nh7bkTO4JlkT3rT_JIBP9jGfc,26
-deepresearch_flow/translator/cli.py,sha256=BceOZhQuN9s5kqhpvLJuwpbB5J0MY1ucWUKw0jXWUPc,16872
+deepresearch_flow/translator/cli.py,sha256=gFcLTltbGqEU8LJl8epPRLEdNrmI03IWV6pbzuW9Z_o,18942
 deepresearch_flow/translator/config.py,sha256=0JI4VBLIzT039YscfEb5hqtCWCu8P2bJIgnAfIAhFmU,502
-deepresearch_flow/translator/engine.py,sha256=dLKKUjmptkLXhIs5ZsIUonmKI9bS8Se4tOnp7fADIYU,36800
+deepresearch_flow/translator/engine.py,sha256=kdr7dkkwHTVkMhN7IpcQ1qGhIIl2mYsRfVeY3FOrbrk,42084
 deepresearch_flow/translator/fixers.py,sha256=Oe9vLhNxkmqyF6SkfTAGLDiSl7N_cCUArhO6pGpIa3Q,15667
 deepresearch_flow/translator/placeholder.py,sha256=mEgqA-dPdOsIhno0h_hzfpXpY2asb4A7UQEYV3tcnP8,2097
-deepresearch_flow/translator/prompts.py,sha256=kl_9O2YvmtXC1w6WLnsLuVZKz4mcOtUF887SiTaOvc0,4754
-deepresearch_flow/translator/protector.py,sha256=sXwNJ1Y8tyPm7dgm8-7S8HkcPe23TGsBdwRxH6mKL70,11291
+deepresearch_flow/translator/prompts.py,sha256=EvfBvBIpQXARDj4m87GAyFXJGL8EJeahj_rOmp9mv68,5556
+deepresearch_flow/translator/protector.py,sha256=yUMuS2FgVofK_MRXrcauLRiwNvdCCjNAnh6CcNd686o,11777
 deepresearch_flow/translator/segment.py,sha256=rBFMCLTrvm2GrPc_hNFymi-8Ih2DAtUQlZHCRE9nLaM,5146
-deepresearch_flow-0.5.1.dist-info/licenses/LICENSE,sha256=hT8F2Py1pe6flxq3Ufdm2UKFk0B8CBm0aAQfsLXfvjw,1063
-deepresearch_flow-0.5.1.dist-info/METADATA,sha256=glpV-vtIAMg05jdBladhGqNxE2p4Dq0Ynd4O3YsmSds,14486
-deepresearch_flow-0.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deepresearch_flow-0.5.1.dist-info/entry_points.txt,sha256=1uIKscs0YRMg_mFsg9NjsaTt4CvQqQ_-zGERUKhhL_Y,65
-deepresearch_flow-0.5.1.dist-info/top_level.txt,sha256=qBl4RvPJNJUbL8CFfMNWxY0HpQLx5RlF_ko-z_aKpm0,18
-deepresearch_flow-0.5.1.dist-info/RECORD,,
+deepresearch_flow-0.6.1.dist-info/licenses/LICENSE,sha256=hT8F2Py1pe6flxq3Ufdm2UKFk0B8CBm0aAQfsLXfvjw,1063
+deepresearch_flow-0.6.1.dist-info/METADATA,sha256=y_CHy1YJ-3P31W43Q_fd8dEkznj7LKLRrCF6F-sGHaQ,26696
+deepresearch_flow-0.6.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+deepresearch_flow-0.6.1.dist-info/entry_points.txt,sha256=1uIKscs0YRMg_mFsg9NjsaTt4CvQqQ_-zGERUKhhL_Y,65
+deepresearch_flow-0.6.1.dist-info/top_level.txt,sha256=qBl4RvPJNJUbL8CFfMNWxY0HpQLx5RlF_ko-z_aKpm0,18
+deepresearch_flow-0.6.1.dist-info/RECORD,,

{deepresearch_flow-0.5.1.dist-info → deepresearch_flow-0.6.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

deepresearch_flow-0.5.1.dist-info/METADATA

@@ -1,440 +0,0 @@
-Metadata-Version: 2.4
-Name: deepresearch-flow
-Version: 0.5.1
-Summary: Workflow tools for paper extraction, review, and research automation.
-Author-email: DengQi <dengqi935@gmail.com>
-License: MIT License
-        
-        Copyright (c) 2025 DengQi
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy
-        of this software and associated documentation files (the "Software"), to deal
-        in the Software without restriction, including without limitation the rights
-        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-        copies of the Software, and to permit persons to whom the Software is
-        furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all
-        copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-        SOFTWARE.
-        
-Project-URL: Homepage, https://github.com/nerdneilsfield/ai-deepresearch-flow
-Project-URL: Repository, https://github.com/nerdneilsfield/ai-deepresearch-flow
-Project-URL: Issues, https://github.com/nerdneilsfield/ai-deepresearch-flow/issues
-Keywords: research,papers,pdf,ocr,llm,workflow
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.12
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: anthropic>=0.28.0
-Requires-Dist: click>=8.1.7
-Requires-Dist: coloredlogs>=15.0.1
-Requires-Dist: dashscope>=1.20.0
-Requires-Dist: google-auth>=2.0.0
-Requires-Dist: google-genai>=0.5.0
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: jinja2>=3.1.3
-Requires-Dist: json-repair>=0.31.0
-Requires-Dist: jsonschema>=4.21.1
-Requires-Dist: markdown-it-py>=3.0.0
-Requires-Dist: mdit-py-plugins>=0.4.0
-Requires-Dist: pypdf>=3.0.0
-Requires-Dist: pylatexenc>=2.10
-Requires-Dist: pybtex>=0.24.0
-Requires-Dist: rich>=13.7.1
-Requires-Dist: rumdl>=0.0.218
-Requires-Dist: starlette>=0.37.2
-Requires-Dist: tqdm>=4.66.4
-Requires-Dist: uvicorn>=0.27.1
-Dynamic: license-file
-
-<p align="center">
-  <img src=".github/assets/logo.png" width="140" alt="ai-deepresearch-flow logo" />
-</p>
-
-<h3 align="center">ai-deepresearch-flow</h3>
-
-<p align="center">
-  <em>From documents to deep research insight — automatically.</em>
-</p>
-
-<p align="center">
-  <a href="README.md">English</a> | <a href="README_ZH.md">中文</a>
-</p>
-
-<p align="center">
-  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/actions">
-    <img src="https://img.shields.io/github/actions/workflow/status/nerdneilsfield/ai-deepresearch-flow/push-to-pypi.yml?style=flat-square" />
-  </a>
-  <a href="https://pypi.org/project/deepresearch-flow/">
-    <img src="https://img.shields.io/pypi/v/deepresearch-flow?style=flat-square" />
-  </a>
-  <a href="https://pypi.org/project/deepresearch-flow/">
-    <img src="https://img.shields.io/pypi/pyversions/deepresearch-flow?style=flat-square" />
-  </a>
-  <a href="https://hub.docker.com/r/nerdneils/deepresearch-flow">
-    <img src="https://img.shields.io/docker/v/nerdneils/deepresearch-flow?style=flat-square" />
-  </a>
-  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/pkgs/container/deepresearch-flow">
-    <img src="https://img.shields.io/badge/ghcr.io-nerdneilsfield%2Fdeepresearch-flow-0f172a?style=flat-square" />
-  </a>
-  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/blob/main/LICENSE">
-    <img src="https://img.shields.io/github/license/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
-  </a>
-  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/stargazers">
-    <img src="https://img.shields.io/github/stars/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
-  </a>
-  <a href="https://pypi.org/project/deepresearch-flow">
-  <img alt="PyPI - Version" src="https://img.shields.io/pypi/v/deepresearch-flow">
-  </a>
-  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/issues">
-    <img src="https://img.shields.io/github/issues/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
-  </a>
-</p>
-
----
-
-## The Core Pain Points
-
-- **OCR Chaos**: Raw markdown from OCR tools is often broken -- tables drift, formulas break, and references are non-clickable.
-- **Translation Nightmares**: Translating technical papers often destroys code blocks, LaTeX formulas, and table structures.
-- **Information Overload**: Extracting structured insights (authors, venues, summaries) from hundreds of PDFs manually is impossible.
-- **Context Switching**: Managing PDFs, summaries, and translations in different windows kills focus.
-
-## The Solution
-
-DeepResearch Flow provides a unified pipeline to **Repair**, **Translate**, **Extract**, and **Serve** your research library.
-
-## Key Features
-
-- **Smart Extraction**: Turn unstructured Markdown into schema-enforced JSON (summaries, metadata, Q&A) using LLMs (OpenAI, Claude, Gemini, etc.).
-- **Precision Translation**: Translate OCR Markdown to Chinese/Japanese (`.zh.md`, `.ja.md`) while **freezing** formulas, code, tables, and references. No more broken layout.
-- **Local Knowledge DB**: A high-performance local Web UI to browse papers with **Split View** (Source vs. Translated vs. Summary), full-text search, and multi-dimensional filtering.
-- **Coverage Compare**: Compare JSON/PDF/Markdown/Translated datasets to find missing artifacts and export CSV reports.
-- **OCR Post-Processing**: Automatically fix broken references (`[1]` -> `[^1]`), merge split paragraphs, and standardize layouts.
-
----
-
-## Quick Start
-
-### 1) Installation
-
-```bash
-# Recommended: using uv for speed
-uv pip install deepresearch-flow
-
-# Or standard pip
-pip install deepresearch-flow
-```
-
-### 2) Configuration
-
-Set up your LLM providers. We support OpenAI, Claude, Gemini, Ollama, and more.
-
-```bash
-cp config.example.toml config.toml
-# Edit config.toml to add your API keys (e.g., env:OPENAI_API_KEY)
-```
-
-### 3) The "Zero to Hero" Workflow
-
-#### Step 1: Extract Insights
-
-Scan a folder of markdown files and extract structured summaries.
-
-```bash
-uv run deepresearch-flow paper extract \
-  --input ./docs \
-  --model openai/gpt-4o-mini \
-  --prompt-template deep_read
-```
-
-#### Step 2: Translate Safely
-
-Translate papers to Chinese, protecting LaTeX and tables.
-
-```bash
-uv run deepresearch-flow translator translate \
-  --input ./docs \
-  --target-lang zh \
-  --model openai/gpt-4o-mini \
-  --fix-level moderate
-```
-
-#### Step 3: Repair OCR Outputs (Recommended)
-
-Recommended sequence to stabilize markdown before serving:
-
-```bash
-# 1) Fix OCR markdown (auto-detects JSON if inputs are .json)
-uv run deepresearch-flow recognize fix \
-  --input ./docs \
-  --in-place
-
-# 2) Fix LaTeX formulas
-uv run deepresearch-flow recognize fix-math \
-  --input ./docs \
-  --model openai/gpt-4o-mini \
-  --in-place
-
-# 3) Fix Mermaid diagrams
-uv run deepresearch-flow recognize fix-mermaid \
-  --input ./paper_outputs \
-  --json \
-  --model openai/gpt-4o-mini \
-  --in-place
-
-# 4) Fix again to normalize formatting
-uv run deepresearch-flow recognize fix \
-  --input ./docs \
-  --in-place
-```
-
-#### Step 4: Serve Your Database
-
-Launch a local UI to read and manage your papers.
-
-```bash
-uv run deepresearch-flow paper db serve \
-  --input paper_infos.json \
-  --md-root ./docs \
-  --md-translated-root ./docs \
-  --host 127.0.0.1
-```
-
----
-
-## Deployment (Static CDN)
-
-Use a separate static server (CDN) for PDFs/Markdown/images and keep the API/UI on another host.
-
-### 1) Export static assets
-
-```bash
-uv run deepresearch-flow paper db serve \
-  --input paper_infos.json \
-  --md-root ./docs \
-  --md-translated-root ./docs \
-  --pdf-root ./pdfs \
-  --static-mode prod \
-  --static-base-url https://static.example.com \
-  --static-export-dir /data/paper-static
-```
-
-Notes:
-- The API host must be able to read the original PDF/Markdown roots to build the index and hashes.
-- The CDN host only needs the exported directory (e.g. `/data/paper-static`).
-
-### 2) Serve the export directory with CORS + cache headers (Caddy example)
-
-```caddyfile
-:8002 {
-  root * /data/paper-static
-  encode zstd gzip
-
-  @static path /pdf/* /md/* /md_translate/* /images/*
-  header @static {
-    Access-Control-Allow-Origin *
-    Access-Control-Allow-Methods GET,HEAD,OPTIONS
-    Access-Control-Allow-Headers *
-    Cache-Control "public, max-age=31536000, immutable"
-  }
-
-  @options method OPTIONS
-  respond @options 204
-
-  file_server
-}
-```
-
-### 3) Start the API/UI with static base
-
-```bash
-export PAPER_DB_STATIC_BASE_URL="https://static.example.com"
-export PAPER_DB_STATIC_MODE="prod"
-export PAPER_DB_STATIC_EXPORT_DIR="/data/paper-static"
-export PAPER_DB_PDFJS_CDN_BASE_URL="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/4.0.379"
-
-uv run deepresearch-flow paper db serve \
-  --input paper_infos.json \
-  --md-root ./docs \
-  --md-translated-root ./docs \
-  --pdf-root ./pdfs
-```
-
----
-
-## Comprehensive Guide
-
-<details>
-<summary><strong>1. Translator: OCR-Safe Translation</strong></summary>
-
-The translator module is built for scientific documents. It uses a node-based architecture to ensure stability.
-
-- Structure Protection: automatically detects and "freezes" code blocks, LaTeX (`$$...$$`), HTML tables, and images before sending text to the LLM.
-- OCR Repair: use `--fix-level` to merge broken paragraphs and convert text references (`[1]`) to clickable Markdown footnotes (`[^1]`).
-- Context-Aware: supports retries for failed chunks and falls back gracefully.
-
-```bash
-# Translate with structure protection and OCR repairs
-uv run deepresearch-flow translator translate \
-  --input ./paper.md \
-  --target-lang ja \
-  --fix-level aggressive \
-  --model claude/claude-3-5-sonnet-20240620
-```
-
-</details>
-
-<details>
-<summary><strong>2. Paper Extract: Structured Knowledge</strong></summary>
-
-Turn loose markdown files into a queryable database.
-
-- Templates: built-in prompts like `simple`, `eight_questions`, and `deep_read` guide the LLM to extract specific insights.
-- Async and throttled: precise control over concurrency (`--max-concurrency`) and rate limits (`--sleep-every`).
-- Incremental: skips already processed files; resumes from where you left off.
-
-```bash
-uv run deepresearch-flow paper extract \
-  --input ./library \
-  --output paper_data.json \
-  --template-dir ./my-custom-prompts \
-  --max-concurrency 10
-```
-
-</details>
-
-<details>
-<summary><strong>3. Database and UI: Your Personal ArXiv</strong></summary>
-
-The db serve command creates a local research station.
-
-- Split View: read the original PDF/Markdown on the left and the Summary/Translation on the right.
-- Full Text Search: search by title, author, year, or content tags (`tag:fpga year:2023..2024`).
-- Stats: visualize publication trends and keyword frequencies.
-- PDF Viewer: built-in PDF.js viewer prevents cross-origin issues with local files.
-
-```bash
-uv run deepresearch-flow paper db serve \
-  --input paper_infos.json \
-  --pdf-root ./pdfs \
-  --cache-dir .cache/db
-```
-
-</details>
-
-<details>
-<summary><strong>4. Paper DB Compare: Coverage Audit</strong></summary>
-
-Compare two datasets (A/B) to find missing PDFs, markdowns, translations, or JSON items, with match metadata.
-
-```bash
-uv run deepresearch-flow paper db compare \
-  --input-a ./a.json \
-  --md-root-b ./md_root \
-  --output-csv ./compare.csv
-
-# Compare translated markdowns by language
-uv run deepresearch-flow paper db compare \
-  --md-translated-root-a ./translated_a \
-  --md-translated-root-b ./translated_b \
-  --lang zh
-```
-
-</details>
-
-<details>
-<summary><strong>5. Recognize: OCR Post-Processing</strong></summary>
-
-Tools to clean up raw outputs from OCR engines like MinerU.
-
-- Embed Images: convert local image links to Base64 for a portable single-file Markdown.
-- Unpack Images: extract Base64 images back to files.
-- Organize: flatten nested OCR output directories.
-- Fix: apply OCR fixes and rumdl formatting during organize, or as a standalone step.
-- Fix JSON: apply the same fixes to markdown fields inside paper JSON outputs.
-- Fix Math: validate and repair LaTeX formulas with optional LLM assistance.
-- Fix Mermaid: validate and repair Mermaid diagrams (requires `mmdc` from mermaid-cli).
-- Recommended order: `fix` -> `fix-math` -> `fix-mermaid` -> `fix`.
-
-```bash
-uv run deepresearch-flow recognize md embed --input ./raw_ocr --output ./clean_md
-```
-
-```bash
-# Organize MinerU output and apply OCR fixes
-uv run deepresearch-flow recognize organize \
-  --input ./mineru_outputs \
-  --output-simple ./ocr_md \
-  --fix
-
-# Fix and format existing markdown outputs
-uv run deepresearch-flow recognize fix \
-  --input ./ocr_md \
-  --output ./ocr_md_fixed
-
-# Fix in place
-uv run deepresearch-flow recognize fix \
-  --input ./ocr_md \
-  --in-place
-
-# Fix JSON outputs in place
-uv run deepresearch-flow recognize fix \
-  --json \
-  --input ./paper_outputs \
-  --in-place
-
-# Fix LaTeX formulas in markdown
-uv run deepresearch-flow recognize fix-math \
-  --input ./docs \
-  --model openai/gpt-4o-mini \
-  --in-place
-
-# Fix Mermaid diagrams in JSON outputs
-uv run deepresearch-flow recognize fix-mermaid \
-  --json \
-  --input ./paper_outputs \
-  --model openai/gpt-4o-mini \
-  --in-place
-```
-
-</details>
-
----
-
-## Docker Support
-
-Don't want to manage Python environments?
-
-```bash
-docker run --rm -v $(pwd):/app -it ghcr.io/nerdneilsfield/deepresearch-flow --help
-```
-
-## Configuration
-
-The config.toml is your control center. It supports:
-
-- Multiple Providers: mix and match OpenAI, DeepSeek (DashScope), Gemini, Claude, and Ollama.
-- Model Routing: explicit routing to specific models (`--model provider/model_name`).
-- Environment Variables: keep secrets safe using `env:VAR_NAME` syntax.
-
-See `config.example.toml` for a full reference.
-
----
-
-<p align="center">
-  Built with love for the Open Science community.
-</p>