Commit Graph

266 Commits

Author SHA1 Message Date
cognitivetech
2564f8d2bb fix(settings): correct yaml multiline string (#1403) 2023-12-16 19:02:46 +01:00
Eliott Bouhana
4e496e970a docs: remove misleading comment about pgpt working with python 3.12 (#1394)
I was misled into believing I could install using python 3.12 whereas the pyproject.toml explicitly states otherwise. This PR only removes this comment to make sure other people are not also trapped 😄
2023-12-15 21:35:02 +01:00
Federico Grandi
3582764801 ci: fix preview docs checkout ref (#1393) 2023-12-12 20:33:34 +01:00
Federico Grandi
1d28ae2915 docs: fix minor capitalization typo (#1392) 2023-12-12 20:31:38 +01:00
github-actions[bot]
e8ac51bba4 chore(main): release 0.2.0 (#1387)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
v0.2.0
2023-12-10 20:08:12 +01:00
3ly-13
145f3ec9f4 feat(ui): Allows User to Set System Prompt via "Additional Options" in Chat Interface (#1353) 2023-12-10 19:45:14 +01:00
3ly-13
a072a40a7c Allow setting OpenAI model in settings (#1386)
feat(settings): Allow setting openai model to be used. Default to GPT 3.5
2023-12-09 20:13:00 +01:00
Louis Melchior
a3ed14c58f feat(llm): drop default_system_prompt (#1385)
As discussed on Discord, the decision has been made to remove the system prompts by default, to better segregate the API and the UI usages.

A concurrent PR (#1353) is enabling the dynamic setting of a system prompt in the UI.

Therefore, if UI users want to use a custom system prompt, they can specify one directly in the UI.
If the API users want to use a custom prompt, they can pass it directly into their messages that they are passing to the API.

In the highlight of the two use case above, it becomes clear that default system_prompt does not need to exist.
2023-12-08 23:13:51 +01:00
Iván Martínez
f235c50be9 Delete old docs (#1384) 2023-12-08 22:39:23 +01:00
EEmlan
9302620eac Adding german speaking model to documentation (#1374) 2023-12-08 11:26:25 +01:00
Max Zangs
9cf972563e Add setup option to Makefile (#1368) 2023-12-08 10:34:12 +01:00
github-actions[bot]
3d301d0c6f chore(main): release 0.1.0 (#1094)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
v0.1.0
2023-12-01 14:45:54 +01:00
lopagela
56af625d71 Fix the parallel ingestion mode, and make it available through conf (#1336)
* Fix the parallel ingestion mode, and make it available through conf

Also updated the documentation to show how to configure the ingest mode.

* PR feedback: redirect to documentation
2023-11-30 11:41:55 +01:00
Francisco García Sierra
b7ca7d35a0 Update ingest api docs with Windows support (#1289) 2023-11-29 20:56:37 +01:00
ishaandatta
28d03fdda8 Adding working combination of LLM and Embedding Model to recipes (#1315)
Co-authored-by: ishaandatta <ishaandatta50@gmail.com>
2023-11-29 20:54:22 +01:00
Phi Long
aabdb046ae Add docker compose (#1277)
Co-authored-by: philongn <philongn@theugroup.co>
Co-authored-by: Pablo Orgaz <pabloogc@gmail.com>
2023-11-29 16:46:40 +01:00
Iván Martínez
64ed9cd872 Allow passing a system prompt (#1318) 2023-11-29 15:51:19 +01:00
Gianni Acquisto
9c192ddd73 Added max_new_tokens as a config option to llm yaml block (#1317)
* added max_new_tokens as a configuration option to the llm block in settings

* Update fern/docs/pages/manual/settings.mdx

Co-authored-by: lopagela <lpglm@orange.fr>

* Update private_gpt/settings/settings.py

Add default value for max_new_tokens = 256

Co-authored-by: lopagela <lpglm@orange.fr>

* Addressed location of docs comment

* reformatting from running 'make check'

* remove default config value from settings.yaml

---------

Co-authored-by: lopagela <lpglm@orange.fr>
2023-11-26 19:17:29 +01:00
Gianni Acquisto
baf29f06fa Adding docs about embeddings settings + adding the embedding.mode: local in mock profile (#1316) 2023-11-26 17:32:11 +01:00
lopagela
bafdd3baf1 Ingestion Speedup Multiple strategy (#1309) 2023-11-25 20:12:09 +01:00
Iván Martínez
546ba33e6f Update readme with supporters info (#1311) 2023-11-25 18:35:59 +01:00
Iván Martínez
944c43bfa8 Multi language support - fern debug (#1307)
---------

Co-authored-by: Louis <lpglm@orange.fr>
Co-authored-by: LeMoussel <cnhx27@gmail.com>
2023-11-25 14:34:23 +01:00
Iván Martínez
e8d88f8952 Update preview-docs.yml
Use pull_request_target to be able to access FERN publication secret
2023-11-25 10:14:04 +01:00
Iván Martínez
c6d6e0e71b Update preview-docs.yml to enable debug 2023-11-24 17:51:33 +01:00
Iván Martínez
510caa576b Make qdrant the default vector db (#1285)
* Make qdrant the default vector db

---------

Co-authored-by: Pablo Orgaz <pabloogc@gmail.com>
Co-authored-by: lopagela <lpglm@orange.fr>
2023-11-20 16:19:22 +01:00
Francisco García Sierra
f1cbff0fb7 fix: Windows permission error on ingest service tmp files (#1280) 2023-11-20 10:08:03 +01:00
lopagela
a09cd7a892 Update llama_index to 0.9.3 (#1278)
* Update llama_index to 0.9.3

Had to change some imports because of breaking change durin the llama_index update to 0.9.0

* Update poetry.lock after update of llama_index
2023-11-19 18:49:36 +01:00
lopagela
36f69eed0f Refactor documentation architecture (#1264)
* Refactor documentation architecture

Split into several `tab` and sections

* Fix Fern's docs.yml after PR review

Thank you Danny!

Co-authored-by: dannysheridan <danny@buildwithfern.com>

* Re-add quickstart in the overview tab

It went missing after a refactoring of the doc architecture

* Documentation writing

* Adapt Makefile to fern documentation

* Do not create overlapping page names in fern documentation

This is causing 500. Thank you to @dsinghvi for the troubleshooting and the help!

* Add a readme to help to understand how fern documentation work and how to add new pages

* Rework the welcome view

Redirects directly users to installation guide with links for people that are not familiar with documentation browsing.

* Simplify the quickstart guide

* PR feedback on installation guide

A ton of refactoring can still be made there

* PR feedback on ingestion

* PR feedback on ingestion splitting

* Rename section on LLM

* Fix missing word in list of LLMs

---------

Co-authored-by: dannysheridan <danny@buildwithfern.com>
2023-11-19 18:46:09 +01:00
Iván Martínez
57a829a8e8 Move fern workflows to root workflows folder (#1273)
* Move fern workflows to root workflows folder

* Only run fern actions when docu has changed
2023-11-18 20:47:44 +01:00
Iván Martínez
8af5ed3347 Delete CNAME 2023-11-18 20:23:05 +01:00
lopagela
224812f7f6 Update to gradio 4 and allow upload multiple files at once in UI (#1271) 2023-11-18 20:19:43 +01:00
Iván Martínez
adaa00ccc8 Fix/readme UI image (#1272) 2023-11-18 20:19:03 +01:00
lopagela
99dc670df0 Add badges in the README.md (#1261)
Using https://shields.io/

To have the complete list of badges available, c.f. to their documentation: https://shields.io/badges
2023-11-18 18:47:30 +01:00
lopagela
f7d7b6cd4b Fixed the avatar of the box by using a local file (#1266)
Now rendering a specific file inside the python code
2023-11-18 12:29:27 +01:00
Pablo Orgaz
0d520026a3 fix: Windows 11 failing to auto-delete tmp file (#1260) 2023-11-17 18:23:57 +01:00
Lai Zn
4197ada626 feat: enable resume download for hf_hub_download (#1249) 2023-11-17 00:13:11 +01:00
Iván Martínez
09d9a91946 Create CNAME 2023-11-17 00:07:50 +01:00
Iván Martínez
f339f7608c Move Docs to Fern (#1257) 2023-11-16 23:25:14 +01:00
Iván Martínez
ff7e2bc9dd Delete CNAME 2023-11-16 22:53:00 +01:00
Iván Martínez
2a417d2f61 Fix/qdrant support (#1253)
* Disable check same thread by default to enable disk-based Qdrant local client to work
2023-11-16 13:29:17 +01:00
Dominik Fuchs
23fa530c31 added wipe make command (#1215)
* added `wipe` make command

* Apply suggestions from code review

Thanks for your suggestions, I like to apply them.

Co-authored-by: lopagela <lpglm@orange.fr>

* added `wipe` command to the documentation

* rebased to generate valid openapi.json

---------

Co-authored-by: lopagela <lpglm@orange.fr>
2023-11-16 11:44:02 +01:00
Anush
03d1ae6d70 feat: Qdrant support (#1228)
* feat: Qdrant support

* Update private_gpt/components/vector_store/vector_store_component.py
2023-11-13 21:23:26 +01:00
Iván Martínez
86fc4781d8 Fix openai setting literal (#1221) 2023-11-12 22:29:26 +01:00
Pablo Orgaz
022bd718e3 fix: Remove global state (#1216)
* Remove all global settings state

* chore: remove autogenerated class

* chore: cleanup

* chore: merge conflicts
2023-11-12 22:20:36 +01:00
Iván Martínez
f394ca61bb Reuse existing stored index during ingestion (#1220) 2023-11-12 22:14:38 +01:00
lopagela
aa70d3d9f0 Add simple Basic auth (#1203)
* Add simple Basic auth

To enable the basic authentication, one must set `server.auth.enabled`
to true.

The static string defined in `server.auth.secret` must be set in the
header `Authorization`.

The health check endpoint will always be accessible, no matter the API
auth configuration.

* Fix linting and type check

* Fighting with mypy being too restrictive

Had to disable mypy in the `auth` as we are not using the same signature
for the authenticated method.

mypy was complaining that the signatures of `authenticated` must be
identical, no matter in which logical branch we are.
Given that fastapi is accomodating itself of method signatures (it will
inject the dependencies in the method call), this warning of mypy is
actually preventing us to do something legit.

mypy doc: https://mypy.readthedocs.io/en/stable/common_issues.html

* Write tests to verify that the simple auth is working
2023-11-12 19:05:00 +01:00
Iván Martínez
b7647542f4 Curate sources to avoid the UI crashing (#1212)
* Curate sources to avoid the UI crashing

* Remove sources from chat history to avoid confusing the LLM
2023-11-12 10:59:51 +01:00
lopagela
a579c9bdc5 Update poetry lock (#1209)
* Update the version of llama_index used to fix transient openai errors

* Update poetry.lock file

* Make `local` mode the default mode by default
2023-11-11 22:44:19 +01:00
Iván Martínez
a22969ad1f Add sources to completions APIs and UI (#1206) 2023-11-11 21:39:15 +01:00
César García
dbd99e7b4b Update description.md (#1107)
Added a section on how to customize low level args, proposing people to stick to suggested models.
2023-11-11 09:23:46 +01:00