Commit Graph

1729 Commits

Author SHA1 Message Date
Stan Girard
0239d5d19c feat(porter): Add Porter.yaml files for backend and frontend services 2024-04-25 10:51:10 +02:00
Stan Girard
5a70735036
chore(main): release 0.0.237 (#2482)
🤖 I have created a release *beep* *boop*
---


## 0.0.237 (2024-04-24)

## What's Changed
* docs: Add environment variables, increase user usage, and add new
models by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2481
* fix(frontend): Warning for Quivr Assistants by @Zewed in
https://github.com/QuivrHQ/quivr/pull/2479
* fix(frontend): better UI for Onboarding by @Zewed in
https://github.com/QuivrHQ/quivr/pull/2477
* docs: add new configuration items by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2483
* Revert "fix(frontend): better UI for Onboarding" by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2485
* feat(reranker): Add flashrank and contextual compression retriever by
@StanGirard in https://github.com/QuivrHQ/quivr/pull/2480
* feat(history): max tokens in the history provided by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2487
* feat: Update chunk overlap to 200 by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2488
* docs: Add reranking configuration guide by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2489
* docs: Update telemetry configuration in Quivr by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2490


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.236...v0.0.237

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-25 01:03:24 -07:00
Stan Girard
5a306b15cb
docs: Update telemetry configuration in Quivr (#2490)
This pull request updates the telemetry configuration in Quivr. The
guide now includes instructions on how to deactivate or configure the
telemetry service.
2024-04-24 14:29:20 -07:00
Stan Girard
0559075cd3
docs: Add reranking configuration guide (#2489)
This pull request adds a new guide to the documentation that explains
how to configure reranking in Quivr. The guide covers the steps to
configure the reranking service using the FlashrankRerank library and
the Cohere ReRanker. It also provides information on the required
environment variables and the default behavior of the Ranker.
2024-04-24 14:26:28 -07:00
Stan Girard
47491bc967
feat: Update chunk overlap to 200 (#2488)
This pull request updates the chunk overlap value in the File class from
300 to 200. This change reduces the overlap between chunks, improving
the performance of chunking operations.
2024-04-24 14:15:31 -07:00
Stan Girard
5c5e022990
feat(history): max tokens in the history provided (#2487)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-24 14:09:55 -07:00
Stan Girard
f656dbcb42
feat(reranker): Add flashrank and contextual compression retriever (#2480)
This pull request adds the flashrank and contextual compression
retriever to the codebase. The flashrank reranker model is used for
compression, and the contextual compression retriever combines the base
compressor and base retriever to improve document retrieval.
2024-04-24 10:44:31 -07:00
Stan Girard
7ead787626
Revert "fix(frontend): better UI for Onboarding" (#2485)
Reverts QuivrHQ/quivr#2477
2024-04-24 05:37:59 -07:00
Stan Girard
d54f370ed4
docs: add new configuration items (#2483)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-24 03:34:24 -07:00
Antoine Dewez
b33e00672a
fix(frontend): better UI for Onboarding (#2477)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-24 01:01:54 -07:00
Antoine Dewez
fe8cfe78ca
fix(frontend): Warning for Quivr Assistants (#2479)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-24 00:57:45 -07:00
Stan Girard
56e79207bb
docs: Add environment variables, increase user usage, and add new models (#2481)
This pull request adds environment variables, increases user usage, and
adds new models to the Quivr application. It includes the following
commits:

- docs: Add environment variables, increase user usage, and add new
models
2024-04-23 15:55:43 -07:00
Stan Girard
f8693e223a
chore(main): release 0.0.236 (#2466)
🤖 I have created a release *beep* *boop*
---


## 0.0.236 (2024-04-23)

## What's Changed
* feat(docs): update to new by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2465
* feat(docs): Add new brain files and update navigation by @StanGirard
in https://github.com/QuivrHQ/quivr/pull/2467
* Feat/docs category brains agents by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2469
* fix(docs): update doc by @Zewed in
https://github.com/QuivrHQ/quivr/pull/2470
* feat(digital-ocean): Update deployment instructions for Digital Ocean
by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2472
* docs(digital-ocean): added missing photo by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2473
* docs: Update brain documentation and images by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2475


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.235...v0.0.236

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-23 07:37:37 -07:00
Stan Girard
751d849b5e
docs: Update brain documentation and images (#2475)
This pull request updates the documentation and images for the default
brain in Quivr. It includes instructions on how to get started,
customize the brain, and ask questions. Additionally, it adds
documentation for the GPT-4 brain and provides steps on how to interact
with it.
2024-04-23 02:21:51 -07:00
Stan Girard
6a7a743b8c
docs(digital-ocean): added missing photo (#2473)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-22 16:14:51 -07:00
Stan Girard
b9ea536836
feat(digital-ocean): Update deployment instructions for Digital Ocean (#2472)
This pull request updates the deployment instructions for Digital Ocean
in the Quivr repository. The instructions now include step-by-step
details on creating a Droplet, choosing the Docker image, updating the
.env file, installing Supabase, allowing the firewall, and launching the
project. The new instructions provide a more comprehensive guide for
deploying Quivr on Digital Ocean.
2024-04-22 16:13:14 -07:00
Stan Girard
75a37491fb Add network configuration to docker-compose.yml 2024-04-23 00:46:47 +02:00
Antoine Dewez
8b68aeb64f
fix(docs): update doc (#2470)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-23 00:40:29 +02:00
Stan Girard
777a6d80ea
Feat/docs category brains agents (#2469)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-22 15:33:36 -07:00
Stan Girard
5ab1a6fe21
feat(docs): Add new brain files and update navigation (#2467)
This pull request adds new brain files and updates the navigation to
include the new files.
2024-04-22 09:39:24 -07:00
Stan Girard
0fd99fe5b2
feat(docs): update to new (#2465)
This pull request updates the API documentation to include new sections
on configuring Quivr and contacting the Quivr team. It also removes the
"API Brains" section from the documentation.
2024-04-22 08:34:11 -07:00
Stan Girard
7c694e6ed4
chore(main): release 0.0.235 (#2463)
🤖 I have created a release *beep* *boop*
---


## 0.0.235 (2024-04-21)

## What's Changed
* fix(sources): Remove duplicate sources and add metadata to model
response by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2462


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.234...v0.0.235

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-21 14:54:43 -07:00
Stan Girard
fbddb70f81
fix(sources): Remove duplicate sources and add metadata to model response (#2462)
This pull request fixes the issue of duplicate sources in the model
response and adds metadata to the response. It removes duplicate sources
with the same name and creates a list of unique sources. Additionally,
it includes the generated URLs and sources in the metadata of the model
response.
2024-04-21 14:50:44 -07:00
Stan Girard
98e5feebcc
chore(main): release 0.0.234 (#2461)
🤖 I have created a release *beep* *boop*
---


## 0.0.234 (2024-04-21)

## What's Changed
* fix(gpt4): Refactor GPT4Brain and KnowledgeBrainQA classes to add
non-streaming-saving-answer by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2460


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.233...v0.0.234

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-21 04:12:38 -07:00
Stan Girard
1f48043bb9
fix(gpt4): Refactor GPT4Brain and KnowledgeBrainQA classes to add non-streaming-saving-answer (#2460)
This pull request refactors the GPT4Brain and KnowledgeBrainQA classes
to add the functionality of saving non-streaming answers. It includes
changes to the `generate_answer` method and the addition of the
`save_non_streaming_answer` method. This enhancement improves the
overall functionality and performance of the code.
2024-04-21 04:09:52 -07:00
Stan Girard
ad83d7a927
chore(main): release 0.0.233 (#2455)
🤖 I have created a release *beep* *boop*
---


## 0.0.233 (2024-04-21)

## What's Changed
* refactor: reorg files in backend by @MaximeThoonsen in
https://github.com/QuivrHQ/quivr/pull/2449
* Revert "refactor: reorg files in backend" by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2456
* refactor: Refacto code #1 by @MaximeThoonsen in
https://github.com/QuivrHQ/quivr/pull/2458
* refactor: reorg the files #2 by @MaximeThoonsen in
https://github.com/QuivrHQ/quivr/pull/2457
* feat(gpt4): Add chat service and generate answer method to GPT4Brain
class by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2459

## New Contributors
* @MaximeThoonsen made their first contribution in
https://github.com/QuivrHQ/quivr/pull/2449

**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.232...v0.0.233

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-21 03:47:59 -07:00
Stan Girard
e426ecd178
feat(gpt4): Add chat service and generate answer method to GPT4Brain class (#2459)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-21 03:42:03 -07:00
Thoonsen Maxime
5c965b6d22
refactor: reorg the files #2 (#2457)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-20 02:28:20 -07:00
Thoonsen Maxime
43a20ebefe
refactor: Refacto code #1 (#2458)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-20 02:22:05 -07:00
Stan Girard
ec37400691
Revert "refactor: reorg files in backend" (#2456)
Reverts QuivrHQ/quivr#2449
2024-04-20 01:42:35 -07:00
Thoonsen Maxime
dc6bd53519
refactor: reorg files in backend (#2449)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):


<!--
ELLIPSIS_HIDDEN
-->
----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
997576d577 |
|--------|

### Summary:
This PR involves a significant refactoring of the codebase, with file
and class relocations and renames, and updated import paths, without
introducing new functionality.

**Key points**:
- Significant refactoring of the codebase for improved organization and
clarity.
- File and class relocations and renames.
- Updated import paths to reflect new locations and names.
- No new functionality introduced.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)

<!--
ELLIPSIS_HIDDEN
-->
2024-04-19 22:25:03 -10:00
Stan Girard
1d7b31949d
chore(main): release 0.0.232 (#2452)
🤖 I have created a release *beep* *boop*
---


## 0.0.232 (2024-04-19)

## What's Changed
* Update CPU and memory settings in task definition files by @StanGirard
in https://github.com/QuivrHQ/quivr/pull/2450
* fix: Fix error message in SummaryAssistant class by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2453


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.231...v0.0.232

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
2024-04-19 03:04:00 -07:00
Stan Girard
9301cee76d
fix: Fix error message in SummaryAssistant class (#2453)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):
2024-04-19 03:02:59 -07:00
Stan Girard
0761738082 feat: Fix error message for missing files key in input 2024-04-19 12:01:53 +02:00
Stan Girard
5d92b98bcb Update output description in summary_inputs function 2024-04-19 11:54:38 +02:00
Stan Girard
588e78336b
Update CPU and memory settings in task definition files (#2450)
This pull request updates the CPU and memory settings in the task
definition files for the AWS service. The CPU has been increased from
1024 to 2048, and the memory has been increased from 2048 to 4096. This
change ensures that the service has enough resources to handle the
workload efficiently.

<!--
ELLIPSIS_HIDDEN
-->


----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
1bc415aa66 |
|--------|

### Summary:
This PR enhances the AWS service's resource allocation by doubling the
CPU and memory settings in the task definition files.

**Key points**:
- Updated CPU and memory settings in `/.aws/task_definition.json` and
`/.aws/task_definition_preview.json`.
- CPU value increased from 1024 to 2048.
- Memory value increased from 2048 to 4096.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-19 02:49:03 -07:00
Stan Girard
08c857a9c9
chore(main): release 0.0.231 (#2434)
🤖 I have created a release *beep* *boop*
---


## 0.0.231 (2024-04-19)

## What's Changed
* feat(assistants): Add user usage update and pricing calculation to ITO
assistant by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2433
* feat(assistant): improve prompt summary by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2435
* feat(assistants): Add PDF generation functionality and nice emails by
@StanGirard in https://github.com/QuivrHQ/quivr/pull/2436
* feat(analytics): rely on sql rather that python loop for brains by
@StanGirard in https://github.com/QuivrHQ/quivr/pull/2437
* fix(assistant): summary now can output 2000 tokens by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2440
* feat(assistant): check if key of file is same as filename uploaded by
@StanGirard in https://github.com/QuivrHQ/quivr/pull/2439
* feat: Update Docker build commands and dependencies by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2441
* feat(rag): Refactor DEFAULT_DOCUMENT_PROMPT in quivr_rag.py by
@StanGirard in https://github.com/QuivrHQ/quivr/pull/2442
* Enable Porter Application quivr-back by @porter-deployment-app in
https://github.com/QuivrHQ/quivr/pull/2443
* Enable Porter Application quivr-demo-front by @porter-deployment-app
in https://github.com/QuivrHQ/quivr/pull/2444
* fix(assistants): brain id is null by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2445
* feat(summary): improve prompt to get more insights by @StanGirard in
https://github.com/QuivrHQ/quivr/pull/2446
* feat(aws): Update CPU and memory configurations for task definitions
by @StanGirard in https://github.com/QuivrHQ/quivr/pull/2447
* feat(frontend): Quivr Assistants by @Zewed in
https://github.com/QuivrHQ/quivr/pull/2448


**Full Changelog**:
https://github.com/QuivrHQ/quivr/compare/v0.0.230...v0.0.231

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

<!--
ELLIPSIS_HIDDEN
-->


----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
a16fa4dbaf |
|--------|

### Summary:
This PR releases version 0.0.231, introducing several feature
enhancements and bug fixes across the assistant, analytics, Docker, and
frontend modules.

**Key points**:
- Release version 0.0.231 with feature enhancements and bug fixes across
multiple modules
- User usage update and pricing calculation added to ITO assistant
- Improved prompt summary in assistant module
- PDF generation functionality and email enhancements added
- Analytics optimized by relying on SQL instead of Python loop
- Token output limit fixed in assistant summary
- Docker build commands and dependencies updated
- DEFAULT_DOCUMENT_PROMPT in quivr_rag.py refactored
- Porter Applications for quivr-back and quivr-demo-front enabled
- Null brain id issue fixed in assistants module
- Prompt improved for better insights in summary module
- CPU and memory configurations for AWS task definitions updated
- Quivr Assistants added in frontend


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-19 01:54:32 -07:00
Antoine Dewez
803f304390
feat(frontend): Quivr Assistants (#2448)
# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):


<!--
ELLIPSIS_HIDDEN
-->
----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
3e95f1a5aa |
|--------|

### Summary:
This PR introduces the 'Quivr Assistants' feature with new frontend
components and pages, backend routes and DTOs changes, and a minor
update in the `processAssistant` function.

**Key points**:
- Introduced the 'Quivr Assistants' feature with new frontend components
and pages, backend routes and DTOs changes.
- Added new `AssistantModal` component in
`/frontend/app/assistants/AssistantModal/AssistantModal.tsx`.
- Added new `InputsStep` and `OutputsStep` components for handling
assistant inputs and outputs.
- Added new `AssistantModal` page in
`/frontend/app/assistants/page.tsx`.
- Added new API endpoints and types for assistants in
`/frontend/lib/api/assistants/assistants.ts` and
`/frontend/lib/api/assistants/types.ts`.
- Updated backend assistant routes and DTOs in
`backend/modules/assistant/controller/assistant_routes.py`,
`backend/modules/assistant/dto/inputs.py`,
`backend/modules/assistant/ito/difference.py`, and
`backend/modules/assistant/ito/summary.py`.
- Made a minor update in the `processAssistant` function in the
`/frontend/lib/api/assistants/assistants.ts` file.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)

<!--
ELLIPSIS_HIDDEN
-->
2024-04-19 01:36:36 -07:00
Stan Girard
5876bcfcdc
feat(aws): Update CPU and memory configurations for task definitions (#2447)
This pull request updates the CPU and memory configurations for the task
definitions in the AWS service. The CPU has been changed from 2048 to
1024, and the memory has been changed from 8192 to 2048. These changes
optimize the resource allocation for the task definitions.

<!--
ELLIPSIS_HIDDEN
-->


----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
c095179818 |
|--------|

### Summary:
This PR optimizes resource allocation by reducing CPU and memory
configurations for task definitions in five AWS service JSON files.

**Key points**:
- Reduced CPU and memory configurations in `task_definition.json`,
`task_definition_preview.json`, `task_definition_preview_beat.json`,
`task_definition_preview_worker.json`, and
`task_definition_prod_worker.json`.
- Optimized resource allocation for task definitions.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-18 15:17:46 -07:00
Stan Girard
c3e0c2f2ee
feat(summary): improve prompt to get more insights (#2446)
This pull request includes a commit that improves the prompt used to get
more insights from the document. The commit modifies the map and reduce
templates to provide clearer instructions for analyzing each section of
the document and generating a consolidated summary. The changes also
include adjustments to the text splitter to improve the chunk overlap.

<!--
ELLIPSIS_HIDDEN
-->


----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
adf5541dab |
|--------|

### Summary:
This PR enhances the document analysis and summary generation
instructions in the `SummaryAssistant` class and improves text splitting
by adjusting the `chunk_overlap` parameter.

**Key points**:
- Updated `map_template` and `reduce_template` in `process_assistant`
method of `SummaryAssistant` class in
`/backend/modules/assistant/ito/summary.py`.
- Adjusted `chunk_overlap` parameter of `CharacterTextSplitter` instance
from 0 to 100.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-18 14:04:06 -07:00
Stan Girard
3e53ff0dce
fix(assistants): brain id is null (#2445)
This pull request fixes an issue where the brain activation and value
handling were not working correctly. The `BrainInput` model now allows
for optional activation and value fields, and an empty string is
converted to `None` using a root validator. This ensures that brain
activation and value can be properly handled in the application.

<!--
ELLIPSIS_HIDDEN
-->


----

| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
d63ed6e651 |
|--------|

### Summary:
This PR modifies the `BrainInput` class in
`/backend/modules/assistant/dto/inputs.py` to make `activated` and
`value` fields optional and adds a root validator to convert empty
strings to `None`.

**Key points**:
- Modified `BrainInput` class in
`/backend/modules/assistant/dto/inputs.py`
- Made `activated` and `value` fields optional with default values
- Added root validator `empty_string_to_none` to convert empty strings
to `None`


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-18 14:03:47 -07:00
porter-deployment-app[bot]
e0edaedbd0
Enable Porter Application quivr-demo-front (#2444)
Hello 👋 from Porter! Please merge this PR to finish setting up your
application.

Co-authored-by: porter-deployment-app[bot] <87230664+porter-deployment-app[bot]@users.noreply.github.com>
2024-04-18 09:23:39 -07:00
porter-deployment-app[bot]
c84e15dcff
Enable Porter Application quivr-back (#2443)
Hello 👋 from Porter! Please merge this PR to finish setting up your
application.

Co-authored-by: porter-deployment-app[bot] <87230664+porter-deployment-app[bot]@users.noreply.github.com>
2024-04-18 08:55:42 -07:00
Stan Girard
1e6ff8fce0
feat(rag): Refactor DEFAULT_DOCUMENT_PROMPT in quivr_rag.py (#2442)
This pull request refactors the DEFAULT_DOCUMENT_PROMPT in quivr_rag.py
to improve code readability and maintainability. The unnecessary file
name information has been removed from the prompt template as it is now
included in the vector embedding

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 81939457e6. |
|--------|--------|

### Summary:
This PR refactors the `DEFAULT_DOCUMENT_PROMPT` in `quivr_rag.py` by
removing the file name information from the prompt template, enhancing
code readability and maintainability.

**Key points**:
- Refactored `DEFAULT_DOCUMENT_PROMPT` in `quivr_rag.py`.
- Removed file name information from the prompt template.
- File name information is now included in the vector embedding.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 15:26:24 -07:00
Stan Girard
309666f3fd
feat: Update Docker build commands and dependencies (#2441)
This pull request updates the Docker build commands and dependencies.
2024-04-17 14:37:32 -07:00
Stan Girard
311d9bb15c
feat(assistant): check if key of file is same as filename uploaded (#2439)
This pull request fixes the file key validation in the `check_input`
method. Previously, the method only checked if a file was uploaded and
if the key of the file was "doc_to_summarize". However, it did not check
if the key of the file was the same as the name of the file. This PR
adds a check to ensure that the key of the file is the same as the name
of the file. This improves the accuracy of the file validation process.

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 8f04d832ac. |
|--------|--------|

### Summary:
This PR enhances the file validation process in the `SummaryAssistant`
class by ensuring the key of the uploaded file matches its filename.

**Key points**:
- Added a new file key validation in `check_input` method of
`SummaryAssistant` class.
- The validation checks if the key of the uploaded file matches the
filename.
- This is an additional check to the existing file upload and key
validations.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 13:27:15 -07:00
Stan Girard
1bd7e81b3d
fix(assistant): summary now can output 2000 tokens (#2440)
This pull request increases the token limit for the summary output to
2000 in order to accommodate larger documents.

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 4412ecde83. |
|--------|--------|

### Summary:
This PR increases the token limit for the summary output to 2000 in the
`SummaryAssistant` class to accommodate larger documents.

**Key points**:
- Increased `max_tokens` parameter in `ChatLiteLLM` instance to 2000 in
`process_assistant` function of `SummaryAssistant` class in
`/backend/modules/assistant/ito/summary.py` file.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 08:34:04 -07:00
Stan Girard
3400b8633f
feat(analytics): rely on sql rather that python loop for brains (#2437)
This pull request refactors the get_brains_usages method in the
Analytics class. The changes include improving code readability,
optimizing database queries, and fixing potential bugs.

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit f0ad664673. |
|--------|--------|

### Summary:
This PR optimizes the `get_brains_usages` method in the `Analytics`
class by reducing database calls and improving code readability.

**Key points**:
- Refactored `get_brains_usages` method in `Analytics` class.
- Optimized database query to fetch chat history in one go.
- Improved code readability and formatting.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 07:24:03 -07:00
Stan Girard
b62297341f
feat(assistants): Add PDF generation functionality and nice emails (#2436)
This pull request adds PDF generation functionality and improves the
formatting of emails. It includes a new module for generating PDFs using
the fpdf2 library and updates the email templates to use markdown
formatting for better readability.

<!--
ELLIPSIS_HIDDEN
-->
----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit ccecff77a5. |
|--------|--------|

### Summary:
This PR introduces PDF generation functionality, improves email
formatting, sanitizes filenames, updates various files and dependencies,
and updates `docker-compose.dev.yml`.

**Key points**:
- Added PDF generation functionality using the `fpdf2` library
- Improved email formatting
- Sanitized filenames using the `unidecode` library
- Updated `backend/modules/assistant/ito/ito.py` to generate PDFs and
sanitize filenames
- Added `pdf_generator.py` in `backend/modules/assistant/ito/utils/` for
PDF generation
- Updated `Pipfile` and `Pipfile.lock` in
`backend/modules/assistant/ito/utils/` to include `unidecode`
- Updated `requirements.txt` with new dependencies
- Updated `docker-compose.dev.yml`


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)

<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 06:00:31 -07:00
Stan Girard
ed814de1c6
feat(assistant): improve prompt summary (#2435)
This pull request improves the prompt summary in the assistant code. It
updates the map_template and reduce_template to provide clearer
instructions for identifying main themes, key points, and important
information in each section of a document. The reduce_template also
specifies that the final summary should include the main themes, key
points, and important information of the entire document.

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 456736a41d. |
|--------|--------|

### Summary:
This PR enhances the document summarization process in the
`SummaryAssistant` class by providing clearer instructions for
identifying main themes, key points, and important information in each
section of a document.

**Key points**:
- Updated `map_template` and `reduce_template` in `process_assistant`
function of `SummaryAssistant` class.
- Changes provide clearer instructions for summarizing documents.
- Final summary should include main themes, key points, and important
information of the entire document.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-16 14:03:36 -07:00