c7212ac7cc
fix(LLM): mistral ignoring assistant messages ( #1954 )
...
* fix: mistral ignoring assistant messages
* fix: typing
* fix: fix tests
2024-05-30 15:41:16 +02:00
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
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
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
d13029a046
feat(docs): add privategpt-ts sdk ( #1924 )
2024-05-10 14:13:15 +02:00
9d0d614706
fix: Replacing unsafe `eval()` with `json.loads()` ( #1890 )
2024-04-30 09:58:19 +02:00
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
c1802e7cf0
fix(docs): Update installation.mdx ( #1866 )
...
Update repo url
2024-04-19 17:10:58 +02:00
2a432bf9c5
fix: make embedding_api_base match api_base when on docker ( #1859 )
2024-04-19 15:42:19 +02:00
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
49ef729abc
Allow passing HF access token to download tokenizer. Fallback to default tokenizer.
2024-04-19 15:38:25 +02:00
347be643f7
fix(llm): special tokens and leading space ( #1831 )
2024-04-04 14:37:29 +02:00
08c4ab175e
Fix version in poetry
2024-04-03 10:59:35 +02:00
f469b4619d
Add required Ollama setting
2024-04-02 18:27:57 +02:00
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
8a836e4651
feat(docs): Add guide Llama-CPP Linux AMD GPU support ( #1782 )
2024-04-02 16:55:05 +02:00
f0b174c097
feat(ui): Add Model Information to ChatInterface label
2024-04-02 16:52:27 +02:00
bac818add5
feat(code): improve concat of strings in ui ( #1785 )
2024-04-02 16:42:40 +02:00
ea153fb92f
feat(scripts): Wipe qdrant and obtain db Stats command ( #1783 )
2024-04-02 16:41:42 +02:00
b3b0140e24
feat(llm): Ollama LLM-Embeddings decouple + longer keep_alive settings ( #1800 )
2024-04-02 16:23:10 +02:00
83adc12a8e
feat(RAG): Introduce SentenceTransformer Reranker ( #1810 )
2024-04-02 10:29:51 +02:00
f83abff8bc
feat(docker): set default Docker to use Ollama ( #1812 )
2024-04-01 13:08:48 +02:00
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
774e256052
fix: Fixed docker-compose ( #1758 )
...
* Fixed docker-compose
* Update docker-compose.yaml
2024-03-20 21:36:45 +01:00
6f6c785dac
feat(llm): Ollama timeout setting ( #1773 )
...
* added request_timeout to ollama, default set to 30.0 in settings.yaml and settings-ollama.yaml
* Update settings-ollama.yaml
* Update settings.yaml
* updated settings.py and tidied up settings-ollama-yaml
* feat(UI): Faster startup and document listing (#1763 )
* fix(ingest): update script label (#1770 )
huggingface -> Hugging Face
* Fix lint errors
---------
Co-authored-by: Stephen Gresham <steve@gresham.id.au>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
2024-03-20 21:33:46 +01:00
c2d694852b
feat: wipe per storage type ( #1772 )
2024-03-20 21:31:44 +01:00
7d2de5c96f
fix(ingest): update script label ( #1770 )
...
huggingface -> Hugging Face
2024-03-20 20:23:08 +01:00
348df781b5
feat(UI): Faster startup and document listing ( #1763 )
2024-03-20 19:11:44 +01:00
572518143a
feat(docs): Feature/upgrade docs ( #1741 )
...
* Upgrade fern version
* Add info about SDKs
2024-03-19 21:26:53 +01:00
134fc54d7d
feat(ingest): Created a faster ingestion mode - pipeline ( #1750 )
...
* Unify pgvector and postgres connection settings
* Remove local changes
* Update file pgvector->postgres
* postgresql should be postgres
* Adding pipeline ingestion mode
* disable hugging face parallelism. Continue on file to doc transform failure
* Semaphore to limit docq async workers. ETA reporting
2024-03-19 21:24:46 +01:00
1efac6a3fe
feat(llm - embed): Add support for Azure OpenAI ( #1698 )
...
* Add support for Azure OpenAI
* fix: wrong default api_version
Should be dashes instead of underscores.
see: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference
* fix: code styling
applied "make check" changes
* refactor: extend documentation
* mention azopenai as available option and extras
* add recommended section
* include settings-azopenai.yaml configuration file
* fix: documentation
2024-03-15 16:49:50 +01:00
258d02d87c
fix(docs): Minor documentation amendment ( #1739 )
...
* Unify pgvector and postgres connection settings
* Remove local changes
* Update file pgvector->postgres
* postgresql should be postgres
2024-03-15 16:36:32 +01:00
63de7e4930
feat: unify settings for vector and nodestore connections to PostgreSQL ( #1730 )
...
* Unify pgvector and postgres connection settings
* Remove local changes
* Update file pgvector->postgres
2024-03-15 09:55:17 +01:00
68b3a34b03
feat(nodestore): add Postgres for the doc and index store ( #1706 )
...
* Adding Postgres for the doc and index store
* Adding documentation. Rename postgres database local->simple. Postgres storage dependencies
* Update documentation for postgres storage
* Renaming feature to nodestore
* update docstore -> nodestore in doc
* missed some docstore changes in doc
* Updated poetry.lock
* Formatting updates to pass ruff/black checks
* Correction to unreachable code!
* Format adjustment to pass black test
* Adjust extra inclusion name for vector pg
* extra dep change for pg vector
* storage-postgres -> storage-nodestore-postgres
* Hash change on poetry lock
2024-03-14 17:12:33 +01:00
d17c34e81a
fix(settings): set default tokenizer to avoid running make setup fail ( #1709 )
2024-03-13 09:53:40 +01:00
84ad16af80
feat(docs): upgrade fern ( #1596 )
2024-03-11 23:02:56 +01:00
821bca32e9
feat(local): tiktoken cache within repo for offline ( #1467 )
2024-03-11 22:55:13 +01:00
02dc83e8e9
feat(llm): adds serveral settings for llamacpp and ollama ( #1703 )
2024-03-11 22:51:05 +01:00
410bf7a71f
feat(ui): maintain score order when curating sources ( #1643 )
...
* Update ui.py
Changed 'curated_sources' from a list, in order to maintain score order when returning the curated sources.
* Maintain score order after curating sources
2024-03-11 22:27:30 +01:00
290b9fb084
feat(ui): add sources check to not repeat identical sources ( #1705 )
2024-03-11 22:24:18 +01:00
1b03b369c0
chore(main): release 0.4.0 ( #1628 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2024-03-06 17:53:35 +01:00
45f05711eb
feat: Upgrade to LlamaIndex to 0.10 ( #1663 )
...
* Extract optional dependencies
* Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity
* Support Ollama embeddings
* Upgrade to llamaindex 0.10.14. Remove legacy use of ServiceContext in ContextChatEngine
* Fix vector retriever filters
2024-03-06 17:51:30 +01:00
12f3a39e8a
Update x handle to zylon private gpt ( #1644 )
2024-02-23 15:51:35 +01:00
cd40e3982b
feat(Vector): support pgvector ( #1624 )
2024-02-20 15:29:26 +01:00
066ea5bf28
chore(main): release 0.3.0 ( #1413 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2024-02-16 17:42:39 +01:00
aa13afde07
feat(UI): Select file to Query or Delete + Delete ALL ( #1612 )
...
---------
Co-authored-by: Robin Boone <rboone@sofics.com>
2024-02-16 17:36:09 +01:00
24fb80ca38
fix(UI): Updated ui.py. Frees up the CPU to not be bottlenecked.
...
Updated ui.py to include a small sleep timer while building the stream deltas. This recursive function fires off so quickly to eats up too much of the CPU. This small sleep frees up the CPU to not be bottlenecked. This value can go lower/shorter. But 0.02 or 0.025 seems to work well. (#1589 )
Co-authored-by: root <root@wesgitlabdemo.icl.gtri.org>
2024-02-16 12:52:14 +01:00
6bbec79583
feat(llm): Add support for Ollama LLM ( #1526 )
2024-02-09 15:50:50 +01:00
b178b51451
feat(bulk-ingest): Add --ignored Flag to Exclude Specific Files and Directories During Ingestion ( #1432 )
2024-02-07 19:59:32 +01:00
24fae660e6
feat: Add stream information to generate SDKs ( #1569 )
2024-02-02 16:14:22 +01:00
Pablo Orgaz
Yevhenii Semendiak
jcbonnet-fwd
Fran García
Patrick Peng
icsy7867
Daniel Gallego Vico
Marco Repetto
dividebysandwich
imartinez
github-actions[bot]
Иван
Ingrid Stevens
igeni
Brett England
Robin Boone
machatschek
Ikko Eltociear Ashimine
Otto L
Andrew Jiang
Arun Yadav
Hoffelhas
TQ
Ygal Blum
Nick Smirnov