Code

Support Indexing Docx Files#801

Code

Merged

sabaimran merged 88 commits intokhoj-ai:masterkhoj-ai/khoj:masterfrom MythicalCow:docx-file-supportMythicalCow/khoj:docx-file-supportCopy head branch name to clipboardJun 20, 2024

+193-4

Commits

Commits on May 28, 2024

• UI update for file filtered conversations

  MythicalCow

  committed
  7c6be74

Commits on May 29, 2024

• linter fixes

  MythicalCow

  committed
  599917e

• linter fixes

  MythicalCow

  committed
  cf9f4dd

Commits on May 30, 2024

• UI and API endpoints integrations complete. file querying changes to be completed

  MythicalCow

  committed
  8569092

• UI streamlining by adding a plus button instead of a static search bar

  MythicalCow

  committed
  8640f24

• backend and UI conversation ID based file filtering implemented. file filtering to be added

  MythicalCow

  committed
  0d87a8f

• file filtering based on selected files implemented. further testing and clean up required

  MythicalCow

  committed
  d2a369f

Commits on May 31, 2024

• final touches and unnecessary comments removed.

  MythicalCow

  committed
  75d251d

• adding authentication requirement to file-filters endpoint

  MythicalCow

  authored
  fcc99db

Commits on Jun 2, 2024

• fileobjectadapter created and tested

  MythicalCow

  committed
  e515f04

• removed temp file

  MythicalCow

  committed
  8de18ac

Commits on Jun 3, 2024

• Apply file filters with correct syntax

  sabaimran

  committed
  b727a52

• file object adapter notes for later

  MythicalCow

  committed
  71184d5

• made PR changes for a better user experience

  MythicalCow

  committed
  13d71a1

• Merge branch 'khoj-ai:master' into features/conversation-file-filter

  MythicalCow

  authored
  0c129ca

• padding fix

  MythicalCow

  committed
  9714b63

• Merge branch 'features/conversation-file-filter' of https://github.com/MythicalCow/khoj into features/conversation-file-filter

  MythicalCow

  committed
  649edd0

• small UI improvements

  MythicalCow

  committed
  cd204c7

• embeddings update to handle FileObjects

  MythicalCow

  committed
  4a2233e

• embeddings update to handle FileObjects

  MythicalCow

  committed
  e5c8576

Commits on Jun 4, 2024

• Merge branch 'khoj-ai:master' into features/document-summarization

  MythicalCow

  authored
  ec0b0a5

• save

  MythicalCow

  committed
  312b8c4

• added support for new command: /summarize

  MythicalCow

  committed
  0bf3d57

Commits on Jun 5, 2024

• addressed security risk highlighted in PR.

  MythicalCow

  committed
  60de2b4

• added handling for automatically adding an uploaded file to the current conversation's file filter

  MythicalCow

  committed
  f80654b

• Merge pull request #1 from MythicalCow/features/conversation-file-filter

  Show description for 27e3771
  MythicalCow

  authored
  27e3771

• added integrations between file filter and summarize command with error catching.

  MythicalCow

  committed
  c7ea0d9

• fixed API issue related to duplicate file management

  MythicalCow

  committed
  1f52e9a

• Merge pull request #2 from MythicalCow/features/conversation-file-filter

  Show description for 464576f
  MythicalCow

  authored
  464576f

Commits on Jun 6, 2024

• added query based context to summarization command and added more rigorous error catching

  MythicalCow

  committed
  55d191b

• added critical fix that causes indexer to break on non pdf files

  MythicalCow

  committed
  fef1fe0

• added support for new file type on khoj: docx

  MythicalCow

  committed
  fe025ab

Commits on Jun 7, 2024

• added docx2txt requirement to .toml file

  MythicalCow

  committed
  ececa9a

• removed print statement

  MythicalCow

  committed
  38f71de

• first set of PR fixes

  MythicalCow

  committed
  116b4dd

• finished addressing most PR changes.

  MythicalCow

  committed
  4396b39

Commits on Jun 10, 2024

• fixed config settings method to avoid extra DB calls

  MythicalCow

  committed
  3bdd230

Commits on Jun 13, 2024

• changing tester for pdf to entries

  MythicalCow

  committed
  5d49810

• added markdown support

  MythicalCow

  committed
  fe9283c

• tester fix for markdown

  MythicalCow

  committed
  706da48

• plaintext support and testers updated

  MythicalCow

  committed
  3e4eaab

• Merge branch 'master' of https://github.com/MythicalCow/khoj into features/document-summarization

  MythicalCow

  committed
  dce6290

• merge fixes

  MythicalCow

  committed
  264f174

• database migration fix

  MythicalCow

  committed
  dc291b2

• added support for orgmode to /summarize

  MythicalCow

  committed
  7c05b51

• return type specifier

  MythicalCow

  committed
  7d99d1d

• merge conflict fix?

  MythicalCow

  committed
  6209acf

Commits on Jun 14, 2024

• adding logging

  MythicalCow

  committed
  1851c0e

• Merge branch 'master' of https://github.com/MythicalCow/khoj into features/document-summarization

  MythicalCow

  committed
  435d8e6

• added support for new file type on khoj: docx

  MythicalCow

  committed
  09e99d9

• added docx2txt requirement to .toml file

  MythicalCow

  committed
  2ee0c00

• removed print statement

  MythicalCow

  committed
  bb44910

• Merge branch 'docx-file-support' of https://github.com/MythicalCow/khoj into docx-file-support

  MythicalCow

  committed
  2e03035

• removing .doc allowed file type.

  MythicalCow

  committed
  bebc2ac

• bug fix for update_raw_text adapter

  MythicalCow

  committed
  a538485

• quick print statement remove

  MythicalCow

  committed
  9d2a9c8

• small fixes and file summarization support for docx.

  MythicalCow

  committed
  c9496cb

• resolve merge issues with migration files. keep the old one, add a new one

  sabaimran

  committed
  070bde2

• Add error handling for when file object not found, add summarize command to tool selection

  sabaimran

  committed
  0b2e391

• Merge branch 'master' of github.com:khoj-ai/khoj into features/document-summarization

  sabaimran

  committed
  1da9bc4

• Add summarize support for normal streamed chat, non socket

  sabaimran

  committed
  d19ec47

• Remove print line for file list

  sabaimran

  committed
  2919c16

• added some tests for /summarize command.

  MythicalCow

  committed
  bba083b

Commits on Jun 15, 2024

• additional tests added in

  MythicalCow

  committed
  3344a96

• added support for new file type on khoj: docx

  MythicalCow

  committed
  eb993fb

• added docx2txt requirement to .toml file

  MythicalCow

  committed
  b0909f8

• removed print statement

  MythicalCow

  committed
  1643548

• added support for new file type on khoj: docx

  MythicalCow

  committed
  fa8ef95

• removed print statement

  MythicalCow

  committed
  88ad9ca

• small fixes and file summarization support for docx.

  MythicalCow

  committed
  fa8db61

• resolving conflicting db files

  MythicalCow

  committed
  07df66e

• Merge branch 'docx-file-support' of https://github.com/MythicalCow/khoj into docx-file-support

  MythicalCow

  committed
  6308528

• removing redundant db file

  MythicalCow

  committed
  e609eed

• added support for new file type on khoj: docx

  MythicalCow

  committed
  2bfcb3e

• removed print statement

  MythicalCow

  committed
  aaba9b5

• added support for new file type on khoj: docx

  MythicalCow

  committed
  854afa4

• removed print statement

  MythicalCow

  committed
  b2cdb5f

• small fixes and file summarization support for docx.

  MythicalCow

  committed
  fa45ac5

• removing redundant db file

  MythicalCow

  committed
  d644b64

• Merge branch 'docx-file-support' of https://github.com/MythicalCow/khoj into docx-file-support

  MythicalCow

  committed
  82c26b5

• resolving merge conflict with master

  MythicalCow

  committed
  f83cba6

Commits on Jun 17, 2024

• resolving merge conflict

  MythicalCow

  committed
  d7ef0d8

• added additional tests

  MythicalCow

  committed
  5933042

• Merge branch 'features/document-summarization' into docx-file-support

  MythicalCow

  committed
  c027099

• added tests to offline chat director

  MythicalCow

  committed
  10e2af2

• Merge branch 'features/document-summarization' into docx-file-support

  MythicalCow

  committed
  7edb6fa

• linter fixes

  MythicalCow

  committed
  546c378

Commits on Jun 19, 2024

• Merge remote-tracking branch 'origin' into docx-file-support

  MythicalCow

  committed
  6f94f7d