Yevhenii Semendiak
ea7bfe442b
fix pgvector schema env name
2024-10-30 21:45:13 +02:00
Yevhenii Semendiak
7e79b13bcb
Allow parameterizing Huggingface token in PGPT app
2024-10-17 10:25:28 +03:00
Yevhenii Semendiak
269dc41eb2
enable tests for apolo branch
2024-10-16 11:45:01 +03:00
Yevhenii Semendiak
12c850e410
Merge pull request #3 from neuro-inc/eng-393
...
ENG-393: Use dedicated app, pgvector settings
2024-10-16 11:41:31 +03:00
Yevhenii Semendiak
3dfa105187
ENG-393: Use dedicated app, pgvector settings
2024-10-16 11:36:09 +03:00
Ovchinnikov Konstantyn
69f201a73e
Merge pull request #2 from neuro-inc/feature/migrate-docs
...
Migrate docs to apolo and add pre-requisites
2024-10-15 12:52:26 +01:00
costefan
00e9998a09
added apolo as cli and pre-requisites
2024-10-15 12:32:32 +01:00
Yevhenii Semendiak
f8fdef0f38
Update vLLM config to use llama 3.1 8B by default
2024-09-20 16:32:00 +03:00
Yevhenii Semendiak
1938cac2c2
Fix alpaca context window size
2024-08-02 16:26:16 +03:00
Yevhenii Semendiak
4b33f54d8a
Bump vllm to 0.5.1
2024-07-08 17:50:28 +03:00
Yevhenii Semendiak
df7deefdb4
Downgrade ollama to 0.1.35 since newer version have some issues with H100s
2024-06-01 16:15:03 +03:00
Yevhenii Semendiak
a205a62ea2
Change default preset names, pgvector PGData location
2024-06-01 15:26:54 +03:00
Yevhenii Semendiak
e8b9586127
Add embeddings API key default value
2024-05-21 12:22:49 +03:00
Yevhenii Semendiak
58b2e81b7e
Merge branch 'main' into apolo
2024-05-17 18:22:30 +03:00
Yevhenii Semendiak
fc426e964a
add hf token to settings
2024-05-17 18:20:19 +03:00
Yevhenii Semendiak
3b3e96ad6c
Allow parameterizing OpenAI embeddings component (api_base, key, model) ( #1920 )
...
* Allow parameterizing OpenAI embeddings component (api_base, key, model)
* Update settings
* Update description
2024-05-17 09:52:50 +02:00
Yevhenii Semendiak
17f32a5f92
Use Llama 3
2024-05-11 11:33:11 +03:00
jcbonnet-fwd
45df99feb7
Add timeout parameter for better support of openailike LLM tools on local computer (like LM Studio). ( #1858 )
...
feat(llm): Improve settings of the OpenAILike LLM
2024-05-10 16:44:08 +02:00
Fran García
966af4771d
fix(settings): enable cors by default so it will work when using ts sdk (spa) ( #1925 )
2024-05-10 14:13:46 +02:00
Fran García
d13029a046
feat(docs): add privategpt-ts sdk ( #1924 )
2024-05-10 14:13:15 +02:00
Yevhenii Semendiak
6ec581d172
Add embeddings-openai dependency to dockerfile
2024-05-09 00:58:40 +03:00
Yevhenii Semendiak
90dadda249
Allow parameterizing OpenAI embeddings component (api_base, key, model)
2024-05-09 00:42:55 +03:00
Patrick Peng
9d0d614706
fix: Replacing unsafe eval() with json.loads() ( #1890 )
2024-04-30 09:58:19 +02:00
icsy7867
e21bf20c10
feat: prompt_style applied to all LLMs + extra LLM params. ( #1835 )
...
* Updated prompt_style to be moved to the main LLM setting since all LLMs from llama_index can utilize this. I also included temperature, context window size, max_tokens, max_new_tokens into the openailike to help ensure the settings are consistent from the other implementations.
* Removed prompt_style from llamacpp entirely
* Fixed settings-local.yaml to include prompt_style in the LLM settings instead of llamacpp.
2024-04-30 09:53:10 +02:00
Yevhenii Semendiak
659e0f1a9d
update readme
2024-04-29 16:09:17 +03:00
Yevhenii Semendiak
02e9b0e818
Add README description for app deployment
2024-04-29 16:05:53 +03:00
Yevhenii Semendiak
c922272e15
Build app target
2024-04-29 11:54:45 +03:00
Yevhenii Semendiak
e06a05e8fe
Fix image build
2024-04-29 11:51:13 +03:00
Yevhenii Semendiak
0cc64ca42e
Fix workflow branch name
2024-04-29 11:49:17 +03:00
Yevhenii Semendiak
49203c7a72
Release one more tag (corresponding pgpt version)
2024-04-29 11:47:47 +03:00
Yevhenii Semendiak
613fcd070f
Build & release image
2024-04-29 11:43:20 +03:00
Yevhenii Semendiak
c2b4d4af8c
update readme
2024-04-26 21:16:15 +03:00
Yevhenii Semendiak
00e3e85b81
Run on platform
2024-04-26 16:15:51 +03:00
Daniel Gallego Vico
c1802e7cf0
fix(docs): Update installation.mdx ( #1866 )
...
Update repo url
2024-04-19 17:10:58 +02:00
Marco Repetto
2a432bf9c5
fix: make embedding_api_base match api_base when on docker ( #1859 )
2024-04-19 15:42:19 +02:00
dividebysandwich
947e737f30
fix: "no such group" error in Dockerfile, added docx2txt and cryptography deps ( #1841 )
...
* Fixed "no such group" error in Dockerfile, added docx2txt to poetry so docx parsing works out of the box for docker containers
* added cryptography dependency for pdf parsing
2024-04-19 15:40:00 +02:00
imartinez
49ef729abc
Allow passing HF access token to download tokenizer. Fallback to default tokenizer.
2024-04-19 15:38:25 +02:00
Pablo Orgaz
347be643f7
fix(llm): special tokens and leading space ( #1831 )
2024-04-04 14:37:29 +02:00
imartinez
08c4ab175e
Fix version in poetry
2024-04-03 10:59:35 +02:00
imartinez
f469b4619d
Add required Ollama setting
2024-04-02 18:27:57 +02:00
github-actions[bot]
94ef38cbba
chore(main): release 0.5.0 ( #1708 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2024-04-02 17:45:15 +02:00
Иван
8a836e4651
feat(docs): Add guide Llama-CPP Linux AMD GPU support ( #1782 )
2024-04-02 16:55:05 +02:00
Ingrid Stevens
f0b174c097
feat(ui): Add Model Information to ChatInterface label
2024-04-02 16:52:27 +02:00
igeni
bac818add5
feat(code): improve concat of strings in ui ( #1785 )
2024-04-02 16:42:40 +02:00
Brett England
ea153fb92f
feat(scripts): Wipe qdrant and obtain db Stats command ( #1783 )
2024-04-02 16:41:42 +02:00
Robin Boone
b3b0140e24
feat(llm): Ollama LLM-Embeddings decouple + longer keep_alive settings ( #1800 )
2024-04-02 16:23:10 +02:00
machatschek
83adc12a8e
feat(RAG): Introduce SentenceTransformer Reranker ( #1810 )
2024-04-02 10:29:51 +02:00
Marco Repetto
f83abff8bc
feat(docker): set default Docker to use Ollama ( #1812 )
2024-04-01 13:08:48 +02:00
icsy7867
087cb0b7b7
feat(rag): expose similarity_top_k and similarity_score to settings ( #1771 )
...
* Added RAG settings to settings.py, vector_store and chat_service to add similarity_top_k and similarity_score
* Updated settings in vector and chat service per Ivans request
* Updated code for mypy
2024-03-20 22:25:26 +01:00
Marco Repetto
774e256052
fix: Fixed docker-compose ( #1758 )
...
* Fixed docker-compose
* Update docker-compose.yaml
2024-03-20 21:36:45 +01:00
