Feat/add retriever rerank #1560
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Collaborator
JohnJyong
commented
Nov 17, 2023
JohnJyong
commented
- add full-text-index
- support hybrid search
- support rerank
takatost
approved these changes
Nov 17, 2023
charSLee013
added a commit
to charSLee013/dify
that referenced
this pull request
Nov 24, 2023
* Update README.md (langgenius#1525) * fix: conversation rename always auto generate (langgenius#1530) * new readme (langgenius#1528) * doc: update readme (langgenius#1536) * feat: optimize timezone of server (langgenius#1537) * Doc/update readme patch 1 (langgenius#1538) * feat: add code of conduct (langgenius#1541) * fix: upload image (langgenius#1522) * feat: remove plugin page (langgenius#1544) * update images (langgenius#1548) * update images (langgenius#1549) * fix: upload file not clickable in firefox (langgenius#1552) * feat: supports for new version of openllm (langgenius#1554) * Add some interesting badges :) (langgenius#1558) * Feat/add retriever rerank (langgenius#1560) Co-authored-by: jyong <jyong@dify.ai> * Feat/jp and es (langgenius#1562) * Update README_CN.md * feat: add retriever rank fe (langgenius#1557) Co-authored-by: StyleZhang <jasonapring2015@outlook.com> * fix hybrid search reranking check (langgenius#1563) Co-authored-by: jyong <jyong@dify.ai> * fix the error message (langgenius#1564) Co-authored-by: jyong <jyong@dify.ai> * chore: retrieval docs links and enchance help doc translation (langgenius#1570) * feat: fetch stream compatibility enhance (langgenius#1551) * fix(web): Sidebar create new chat context (langgenius#1569) * Feat/sdk vision support (langgenius#1531) Co-authored-by: Joel <iamjoel007@gmail.com> * fix(api): patch Windows timezone set (langgenius#1575) * feat: configurable invite expiry time (langgenius#1573) * fix: some RAG retrieval bugs (langgenius#1577) Co-authored-by: Joel <iamjoel007@gmail.com> * fix: some text (langgenius#1579) * fix multi retrieval with resource score issue (langgenius#1578) Co-authored-by: jyong <jyong@dify.ai> * feat: add `supported_model_types` field and filter in provider list (langgenius#1581) * Compatible model saving error (langgenius#1582) Co-authored-by: jyong <jyong@dify.ai> * feat: bump version to 0.3.31 (langgenius#1584) * fix: retrieval test page hide rerank model also hide retrieval config (langgenius#1585) * fix: chat on start bug (langgenius#1588) * Update docker-compose.yaml (langgenius#1587) * feat: bump version to 0.3.31-fix1 (langgenius#1589) * fix: safari can not in (langgenius#1590) * feat: add anthropic claude-2.1 support (langgenius#1591) * feat: bump version to 0.3.31-fix2 (langgenius#1592) * fix sql transaction error in statistic API (langgenius#1586) * fix: chat token spent info style (langgenius#1597) * fix weaviate hybrid search issue (langgenius#1600) Co-authored-by: jyong <jyong@dify.ai> * feat: optimize db connections in thread (langgenius#1601) * fix hybrid search when document is none (langgenius#1603) Co-authored-by: jyong <jyong@dify.ai> * Fix/multi thread parameter (langgenius#1604) * feat: bump version to 0.3.31-fix3 (langgenius#1606) --------- Co-authored-by: Luyu Zhang <goocarlos@gmail.com> Co-authored-by: takatost <takatost@users.noreply.github.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: jyong <jyong@dify.ai> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: Ricky <5317425+rickythink@users.noreply.github.com> Co-authored-by: Rhon Joe <east.qrj@gmail.com> Co-authored-by: Garfield Dai <dai.hai@foxmail.com> Co-authored-by: Matri <matri@aifi.com> Co-authored-by: waltcow <waltcow@gmail.com>
charSLee013
added a commit
to charSLee013/dify
that referenced
this pull request
Nov 24, 2023
* Update README.md (langgenius#1525) * fix: conversation rename always auto generate (langgenius#1530) * new readme (langgenius#1528) * doc: update readme (langgenius#1536) * feat: optimize timezone of server (langgenius#1537) * Doc/update readme patch 1 (langgenius#1538) * feat: add code of conduct (langgenius#1541) * fix: upload image (langgenius#1522) * feat: remove plugin page (langgenius#1544) * update images (langgenius#1548) * update images (langgenius#1549) * fix: upload file not clickable in firefox (langgenius#1552) * feat: supports for new version of openllm (langgenius#1554) * Add some interesting badges :) (langgenius#1558) * Feat/add retriever rerank (langgenius#1560) * Feat/jp and es (langgenius#1562) * Update README_CN.md * feat: add retriever rank fe (langgenius#1557) * fix hybrid search reranking check (langgenius#1563) * fix the error message (langgenius#1564) * chore: retrieval docs links and enchance help doc translation (langgenius#1570) * feat: fetch stream compatibility enhance (langgenius#1551) * fix(web): Sidebar create new chat context (langgenius#1569) * Feat/sdk vision support (langgenius#1531) * fix(api): patch Windows timezone set (langgenius#1575) * feat: configurable invite expiry time (langgenius#1573) * fix: some RAG retrieval bugs (langgenius#1577) * fix: some text (langgenius#1579) * fix multi retrieval with resource score issue (langgenius#1578) * feat: add `supported_model_types` field and filter in provider list (langgenius#1581) * Compatible model saving error (langgenius#1582) * feat: bump version to 0.3.31 (langgenius#1584) * fix: retrieval test page hide rerank model also hide retrieval config (langgenius#1585) * fix: chat on start bug (langgenius#1588) * Update docker-compose.yaml (langgenius#1587) * feat: bump version to 0.3.31-fix1 (langgenius#1589) * fix: safari can not in (langgenius#1590) * feat: add anthropic claude-2.1 support (langgenius#1591) * feat: bump version to 0.3.31-fix2 (langgenius#1592) * fix sql transaction error in statistic API (langgenius#1586) * fix: chat token spent info style (langgenius#1597) * fix weaviate hybrid search issue (langgenius#1600) * feat: optimize db connections in thread (langgenius#1601) * fix hybrid search when document is none (langgenius#1603) * Fix/multi thread parameter (langgenius#1604) * feat: bump version to 0.3.31-fix3 (langgenius#1606) --------- Co-authored-by: Luyu Zhang <goocarlos@gmail.com> Co-authored-by: takatost <takatost@users.noreply.github.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: jyong <jyong@dify.ai> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: Ricky <5317425+rickythink@users.noreply.github.com> Co-authored-by: Rhon Joe <east.qrj@gmail.com> Co-authored-by: Garfield Dai <dai.hai@foxmail.com> Co-authored-by: Matri <matri@aifi.com> Co-authored-by: waltcow <waltcow@gmail.com>
HuberyHuV1
pushed a commit
to HuberyHuV1/dify
that referenced
this pull request
Jul 22, 2024
Co-authored-by: jyong <jyong@dify.ai>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.