upload files

.dockerignore

@@ -0,0 +1,12 @@
+.venv
+models
+.github
+.vscode
+.DS_Store
+.mypy_cache
+.ruff_cache
+local_data
+terraform
+tests
+Dockerfile
+Dockerfile.*

.gitignore

@@ -0,0 +1,31 @@
+.venv
+.env
+venv
+
+settings-me.yaml
+
+.ruff_cache
+.pytest_cache
+.mypy_cache
+
+# byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# unit tests / coverage reports
+/tests-results.xml
+/.coverage
+/coverage.xml
+/htmlcov/
+
+# pyenv
+/.python-version
+
+# IDE
+.idea/
+.vscode/
+/.run/
+.fleet/
+
+# macOS
+.DS_Store

.pre-commit-config.yaml

@@ -0,0 +1,43 @@
+default_install_hook_types:
+# Mandatory to install both pre-commit and pre-push hooks (see https://pre-commit.com/#top_level-default_install_hook_types)
+# Add new hook types here to ensure automatic installation when running `pre-commit install`
+- pre-commit
+- pre-push
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.3.0
+  hooks:
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+  - id: check-yaml
+  - id: check-json
+  - id: check-added-large-files
+
+- repo: local
+  hooks:
+  - id: black
+    name: Formatting (black)
+    entry: black
+    language: system
+    types: [python]
+    stages: [commit]
+  - id: ruff
+    name: Linter (ruff)
+    entry: ruff
+    language: system
+    types: [python]
+    stages: [commit]
+  - id: mypy
+    name: Type checking (mypy)
+    entry: make mypy
+    pass_filenames: false
+    language: system
+    types: [python]
+    stages: [commit]
+  - id: test
+    name: Unit tests (pytest)
+    entry: make test
+    pass_filenames: false
+    language: system
+    types: [python]
+    stages: [push]

CHANGELOG.md

@@ -0,0 +1,173 @@
+# Changelog
+
+## [0.6.2](https://github.com/zylon-ai/private-gpt/compare/v0.6.1...v0.6.2) (2024-08-08)
+
+
+### Bug Fixes
+
+* add numpy issue to troubleshooting ([#2048](https://github.com/zylon-ai/private-gpt/issues/2048)) ([4ca6d0c](https://github.com/zylon-ai/private-gpt/commit/4ca6d0cb556be7a598f7d3e3b00d2a29214ee1e8))
+* auto-update version ([#2052](https://github.com/zylon-ai/private-gpt/issues/2052)) ([7fefe40](https://github.com/zylon-ai/private-gpt/commit/7fefe408b4267684c6e3c1a43c5dc2b73ec61fe4))
+* publish image name ([#2043](https://github.com/zylon-ai/private-gpt/issues/2043)) ([b1acf9d](https://github.com/zylon-ai/private-gpt/commit/b1acf9dc2cbca2047cd0087f13254ff5cda6e570))
+* update matplotlib to 3.9.1-post1 to fix win install ([b16abbe](https://github.com/zylon-ai/private-gpt/commit/b16abbefe49527ac038d235659854b98345d5387))
+
+## [0.6.1](https://github.com/zylon-ai/private-gpt/compare/v0.6.0...v0.6.1) (2024-08-05)
+
+
+### Bug Fixes
+
+* add built image from DockerHub ([#2042](https://github.com/zylon-ai/private-gpt/issues/2042)) ([f09f6dd](https://github.com/zylon-ai/private-gpt/commit/f09f6dd2553077d4566dbe6b48a450e05c2f049e))
+* Adding azopenai to model list ([#2035](https://github.com/zylon-ai/private-gpt/issues/2035)) ([1c665f7](https://github.com/zylon-ai/private-gpt/commit/1c665f7900658144f62814b51f6e3434a6d7377f))
+* **deploy:** generate docker release when new version is released ([#2038](https://github.com/zylon-ai/private-gpt/issues/2038)) ([1d4c14d](https://github.com/zylon-ai/private-gpt/commit/1d4c14d7a3c383c874b323d934be01afbaca899e))
+* **deploy:** improve Docker-Compose and quickstart on Docker ([#2037](https://github.com/zylon-ai/private-gpt/issues/2037)) ([dae0727](https://github.com/zylon-ai/private-gpt/commit/dae0727a1b4abd35d2b0851fe30e0a4ed67e0fbb))
+
+## [0.6.0](https://github.com/zylon-ai/private-gpt/compare/v0.5.0...v0.6.0) (2024-08-02)
+
+
+### Features
+
+* bump dependencies ([#1987](https://github.com/zylon-ai/private-gpt/issues/1987)) ([b687dc8](https://github.com/zylon-ai/private-gpt/commit/b687dc852413404c52d26dcb94536351a63b169d))
+* **docs:** add privategpt-ts sdk ([#1924](https://github.com/zylon-ai/private-gpt/issues/1924)) ([d13029a](https://github.com/zylon-ai/private-gpt/commit/d13029a046f6e19e8ee65bef3acd96365c738df2))
+* **docs:** Fix setup docu ([#1926](https://github.com/zylon-ai/private-gpt/issues/1926)) ([067a5f1](https://github.com/zylon-ai/private-gpt/commit/067a5f144ca6e605c99d7dbe9ca7d8207ac8808d))
+* **docs:** update doc for ipex-llm ([#1968](https://github.com/zylon-ai/private-gpt/issues/1968)) ([19a7c06](https://github.com/zylon-ai/private-gpt/commit/19a7c065ef7f42b37f289dd28ac945f7afc0e73a))
+* **docs:** update documentation and fix preview-docs ([#2000](https://github.com/zylon-ai/private-gpt/issues/2000)) ([4523a30](https://github.com/zylon-ai/private-gpt/commit/4523a30c8f004aac7a7ae224671e2c45ec0cb973))
+* **llm:** add progress bar when ollama is pulling models ([#2031](https://github.com/zylon-ai/private-gpt/issues/2031)) ([cf61bf7](https://github.com/zylon-ai/private-gpt/commit/cf61bf780f8d122e4057d002abf03563bb45614a))
+* **llm:** autopull ollama models ([#2019](https://github.com/zylon-ai/private-gpt/issues/2019)) ([20bad17](https://github.com/zylon-ai/private-gpt/commit/20bad17c9857809158e689e9671402136c1e3d84))
+* **llm:** Support for Google Gemini LLMs and Embeddings ([#1965](https://github.com/zylon-ai/private-gpt/issues/1965)) ([fc13368](https://github.com/zylon-ai/private-gpt/commit/fc13368bc72d1f4c27644677431420ed77731c03))
+* make llama3.1 as default ([#2022](https://github.com/zylon-ai/private-gpt/issues/2022)) ([9027d69](https://github.com/zylon-ai/private-gpt/commit/9027d695c11fbb01e62424b855665de71d513417))
+* prompt_style applied to all LLMs + extra LLM params. ([#1835](https://github.com/zylon-ai/private-gpt/issues/1835)) ([e21bf20](https://github.com/zylon-ai/private-gpt/commit/e21bf20c10938b24711d9f2c765997f44d7e02a9))
+* **recipe:** add our first recipe  `Summarize` ([#2028](https://github.com/zylon-ai/private-gpt/issues/2028)) ([8119842](https://github.com/zylon-ai/private-gpt/commit/8119842ae6f1f5ecfaf42b06fa0d1ffec675def4))
+* **vectordb:** Milvus vector db Integration ([#1996](https://github.com/zylon-ai/private-gpt/issues/1996)) ([43cc31f](https://github.com/zylon-ai/private-gpt/commit/43cc31f74015f8d8fcbf7a8ea7d7d9ecc66cf8c9))
+* **vectorstore:** Add clickhouse support as vectore store ([#1883](https://github.com/zylon-ai/private-gpt/issues/1883)) ([2612928](https://github.com/zylon-ai/private-gpt/commit/26129288394c7483e6fc0496a11dc35679528cc1))
+
+
+### Bug Fixes
+
+* "no such group" error in Dockerfile, added docx2txt and cryptography deps ([#1841](https://github.com/zylon-ai/private-gpt/issues/1841)) ([947e737](https://github.com/zylon-ai/private-gpt/commit/947e737f300adf621d2261d527192f36f3387f8e))
+* **config:** make tokenizer optional and include a troubleshooting doc ([#1998](https://github.com/zylon-ai/private-gpt/issues/1998)) ([01b7ccd](https://github.com/zylon-ai/private-gpt/commit/01b7ccd0648be032846647c9a184925d3682f612))
+* **docs:** Fix concepts.mdx referencing to installation page ([#1779](https://github.com/zylon-ai/private-gpt/issues/1779)) ([dde0224](https://github.com/zylon-ai/private-gpt/commit/dde02245bcd51a7ede7b6789c82ae217cac53d92))
+* **docs:** Update installation.mdx ([#1866](https://github.com/zylon-ai/private-gpt/issues/1866)) ([c1802e7](https://github.com/zylon-ai/private-gpt/commit/c1802e7cf0e56a2603213ec3b6a4af8fadb8a17a))
+* ffmpy dependency ([#2020](https://github.com/zylon-ai/private-gpt/issues/2020)) ([dabf556](https://github.com/zylon-ai/private-gpt/commit/dabf556dae9cb00fe0262270e5138d982585682e))
+* light mode ([#2025](https://github.com/zylon-ai/private-gpt/issues/2025)) ([1020cd5](https://github.com/zylon-ai/private-gpt/commit/1020cd53288af71a17882781f392512568f1b846))
+* **LLM:** mistral ignoring assistant messages ([#1954](https://github.com/zylon-ai/private-gpt/issues/1954)) ([c7212ac](https://github.com/zylon-ai/private-gpt/commit/c7212ac7cc891f9e3c713cc206ae9807c5dfdeb6))
+* **llm:** special tokens and leading space ([#1831](https://github.com/zylon-ai/private-gpt/issues/1831)) ([347be64](https://github.com/zylon-ai/private-gpt/commit/347be643f7929c56382a77c3f45f0867605e0e0a))
+* make embedding_api_base match api_base when on docker ([#1859](https://github.com/zylon-ai/private-gpt/issues/1859)) ([2a432bf](https://github.com/zylon-ai/private-gpt/commit/2a432bf9c5582a94eb4052b1e80cabdb118d298e))
+* nomic embeddings ([#2030](https://github.com/zylon-ai/private-gpt/issues/2030)) ([5465958](https://github.com/zylon-ai/private-gpt/commit/54659588b5b109a3dd17cca835e275240464d275))
+* prevent to ingest local files (by default) ([#2010](https://github.com/zylon-ai/private-gpt/issues/2010)) ([e54a8fe](https://github.com/zylon-ai/private-gpt/commit/e54a8fe0433252808d0a60f6a08a43c9f5a42f3b))
+* Replacing unsafe `eval()` with `json.loads()` ([#1890](https://github.com/zylon-ai/private-gpt/issues/1890)) ([9d0d614](https://github.com/zylon-ai/private-gpt/commit/9d0d614706581a8bfa57db45f62f84ab23d26f15))
+* **settings:** enable cors by default so it will work when using ts sdk (spa) ([#1925](https://github.com/zylon-ai/private-gpt/issues/1925)) ([966af47](https://github.com/zylon-ai/private-gpt/commit/966af4771dbe5cf3fdf554b5fdf8f732407859c4))
+* **ui:** gradio bug fixes ([#2021](https://github.com/zylon-ai/private-gpt/issues/2021)) ([d4375d0](https://github.com/zylon-ai/private-gpt/commit/d4375d078f18ba53562fd71651159f997fff865f))
+* unify embedding models ([#2027](https://github.com/zylon-ai/private-gpt/issues/2027)) ([40638a1](https://github.com/zylon-ai/private-gpt/commit/40638a18a5713d60fec8fe52796dcce66d88258c))
+
+## [0.5.0](https://github.com/zylon-ai/private-gpt/compare/v0.4.0...v0.5.0) (2024-04-02)
+
+
+### Features
+
+* **code:** improve concat of strings in ui ([#1785](https://github.com/zylon-ai/private-gpt/issues/1785)) ([bac818a](https://github.com/zylon-ai/private-gpt/commit/bac818add51b104cda925b8f1f7b51448e935ca1))
+* **docker:** set default Docker to use Ollama ([#1812](https://github.com/zylon-ai/private-gpt/issues/1812)) ([f83abff](https://github.com/zylon-ai/private-gpt/commit/f83abff8bc955a6952c92cc7bcb8985fcec93afa))
+* **docs:** Add guide Llama-CPP Linux AMD GPU support ([#1782](https://github.com/zylon-ai/private-gpt/issues/1782)) ([8a836e4](https://github.com/zylon-ai/private-gpt/commit/8a836e4651543f099c59e2bf497ab8c55a7cd2e5))
+* **docs:** Feature/upgrade docs ([#1741](https://github.com/zylon-ai/private-gpt/issues/1741)) ([5725181](https://github.com/zylon-ai/private-gpt/commit/572518143ac46532382db70bed6f73b5082302c1))
+* **docs:** upgrade fern ([#1596](https://github.com/zylon-ai/private-gpt/issues/1596)) ([84ad16a](https://github.com/zylon-ai/private-gpt/commit/84ad16af80191597a953248ce66e963180e8ddec))
+* **ingest:** Created a faster ingestion mode - pipeline ([#1750](https://github.com/zylon-ai/private-gpt/issues/1750)) ([134fc54](https://github.com/zylon-ai/private-gpt/commit/134fc54d7d636be91680dc531f5cbe2c5892ac56))
+* **llm - embed:** Add support for Azure OpenAI ([#1698](https://github.com/zylon-ai/private-gpt/issues/1698)) ([1efac6a](https://github.com/zylon-ai/private-gpt/commit/1efac6a3fe19e4d62325e2c2915cd84ea277f04f))
+* **llm:** adds serveral settings for llamacpp and ollama ([#1703](https://github.com/zylon-ai/private-gpt/issues/1703)) ([02dc83e](https://github.com/zylon-ai/private-gpt/commit/02dc83e8e9f7ada181ff813f25051bbdff7b7c6b))
+* **llm:** Ollama LLM-Embeddings decouple + longer keep_alive settings ([#1800](https://github.com/zylon-ai/private-gpt/issues/1800)) ([b3b0140](https://github.com/zylon-ai/private-gpt/commit/b3b0140e244e7a313bfaf4ef10eb0f7e4192710e))
+* **llm:** Ollama timeout setting ([#1773](https://github.com/zylon-ai/private-gpt/issues/1773)) ([6f6c785](https://github.com/zylon-ai/private-gpt/commit/6f6c785dac2bbad37d0b67fda215784298514d39))
+* **local:** tiktoken cache within repo for offline ([#1467](https://github.com/zylon-ai/private-gpt/issues/1467)) ([821bca3](https://github.com/zylon-ai/private-gpt/commit/821bca32e9ee7c909fd6488445ff6a04463bf91b))
+* **nodestore:** add Postgres for the doc and index store ([#1706](https://github.com/zylon-ai/private-gpt/issues/1706)) ([68b3a34](https://github.com/zylon-ai/private-gpt/commit/68b3a34b032a08ca073a687d2058f926032495b3))
+* **rag:** expose similarity_top_k and similarity_score to settings ([#1771](https://github.com/zylon-ai/private-gpt/issues/1771)) ([087cb0b](https://github.com/zylon-ai/private-gpt/commit/087cb0b7b74c3eb80f4f60b47b3a021c81272ae1))
+* **RAG:** Introduce SentenceTransformer Reranker ([#1810](https://github.com/zylon-ai/private-gpt/issues/1810)) ([83adc12](https://github.com/zylon-ai/private-gpt/commit/83adc12a8ef0fa0c13a0dec084fa596445fc9075))
+* **scripts:** Wipe qdrant and obtain db Stats command ([#1783](https://github.com/zylon-ai/private-gpt/issues/1783)) ([ea153fb](https://github.com/zylon-ai/private-gpt/commit/ea153fb92f1f61f64c0d04fff0048d4d00b6f8d0))
+* **ui:** Add Model Information to ChatInterface label ([f0b174c](https://github.com/zylon-ai/private-gpt/commit/f0b174c097c2d5e52deae8ef88de30a0d9013a38))
+* **ui:** add sources check to not repeat identical sources ([#1705](https://github.com/zylon-ai/private-gpt/issues/1705)) ([290b9fb](https://github.com/zylon-ai/private-gpt/commit/290b9fb084632216300e89bdadbfeb0380724b12))
+* **UI:** Faster startup and document listing ([#1763](https://github.com/zylon-ai/private-gpt/issues/1763)) ([348df78](https://github.com/zylon-ai/private-gpt/commit/348df781b51606b2f9810bcd46f850e54192fd16))
+* **ui:** maintain score order when curating sources ([#1643](https://github.com/zylon-ai/private-gpt/issues/1643)) ([410bf7a](https://github.com/zylon-ai/private-gpt/commit/410bf7a71f17e77c4aec723ab80c233b53765964))
+* unify settings for vector and nodestore connections to PostgreSQL ([#1730](https://github.com/zylon-ai/private-gpt/issues/1730)) ([63de7e4](https://github.com/zylon-ai/private-gpt/commit/63de7e4930ac90dd87620225112a22ffcbbb31ee))
+* wipe per storage type ([#1772](https://github.com/zylon-ai/private-gpt/issues/1772)) ([c2d6948](https://github.com/zylon-ai/private-gpt/commit/c2d694852b4696834962a42fde047b728722ad74))
+
+
+### Bug Fixes
+
+* **docs:** Minor documentation amendment ([#1739](https://github.com/zylon-ai/private-gpt/issues/1739)) ([258d02d](https://github.com/zylon-ai/private-gpt/commit/258d02d87c5cb81d6c3a6f06aa69339b670dffa9))
+* Fixed docker-compose ([#1758](https://github.com/zylon-ai/private-gpt/issues/1758)) ([774e256](https://github.com/zylon-ai/private-gpt/commit/774e2560520dc31146561d09a2eb464c68593871))
+* **ingest:** update script label ([#1770](https://github.com/zylon-ai/private-gpt/issues/1770)) ([7d2de5c](https://github.com/zylon-ai/private-gpt/commit/7d2de5c96fd42e339b26269b3155791311ef1d08))
+* **settings:** set default tokenizer to avoid running make setup fail ([#1709](https://github.com/zylon-ai/private-gpt/issues/1709)) ([d17c34e](https://github.com/zylon-ai/private-gpt/commit/d17c34e81a84518086b93605b15032e2482377f7))
+
+## [0.4.0](https://github.com/imartinez/privateGPT/compare/v0.3.0...v0.4.0) (2024-03-06)
+
+
+### Features
+
+* Upgrade to LlamaIndex to 0.10 ([#1663](https://github.com/imartinez/privateGPT/issues/1663)) ([45f0571](https://github.com/imartinez/privateGPT/commit/45f05711eb71ffccdedb26f37e680ced55795d44))
+* **Vector:** support pgvector ([#1624](https://github.com/imartinez/privateGPT/issues/1624)) ([cd40e39](https://github.com/imartinez/privateGPT/commit/cd40e3982b780b548b9eea6438c759f1c22743a8))
+
+## [0.3.0](https://github.com/imartinez/privateGPT/compare/v0.2.0...v0.3.0) (2024-02-16)
+
+
+### Features
+
+* add mistral + chatml prompts ([#1426](https://github.com/imartinez/privateGPT/issues/1426)) ([e326126](https://github.com/imartinez/privateGPT/commit/e326126d0d4cd7e46a79f080c442c86f6dd4d24b))
+* Add stream information to generate SDKs ([#1569](https://github.com/imartinez/privateGPT/issues/1569)) ([24fae66](https://github.com/imartinez/privateGPT/commit/24fae660e6913aac6b52745fb2c2fe128ba2eb79))
+* **API:** Ingest plain text ([#1417](https://github.com/imartinez/privateGPT/issues/1417)) ([6eeb95e](https://github.com/imartinez/privateGPT/commit/6eeb95ec7f17a618aaa47f5034ee5bccae02b667))
+* **bulk-ingest:** Add --ignored Flag to Exclude Specific Files and Directories During Ingestion ([#1432](https://github.com/imartinez/privateGPT/issues/1432)) ([b178b51](https://github.com/imartinez/privateGPT/commit/b178b514519550e355baf0f4f3f6beb73dca7df2))
+* **llm:** Add openailike llm mode ([#1447](https://github.com/imartinez/privateGPT/issues/1447)) ([2d27a9f](https://github.com/imartinez/privateGPT/commit/2d27a9f956d672cb1fe715cf0acdd35c37f378a5)), closes [#1424](https://github.com/imartinez/privateGPT/issues/1424)
+* **llm:** Add support for Ollama LLM ([#1526](https://github.com/imartinez/privateGPT/issues/1526)) ([6bbec79](https://github.com/imartinez/privateGPT/commit/6bbec79583b7f28d9bea4b39c099ebef149db843))
+* **settings:** Configurable context_window and tokenizer ([#1437](https://github.com/imartinez/privateGPT/issues/1437)) ([4780540](https://github.com/imartinez/privateGPT/commit/47805408703c23f0fd5cab52338142c1886b450b))
+* **settings:** Update default model to TheBloke/Mistral-7B-Instruct-v0.2-GGUF ([#1415](https://github.com/imartinez/privateGPT/issues/1415)) ([8ec7cf4](https://github.com/imartinez/privateGPT/commit/8ec7cf49f40701a4f2156c48eb2fad9fe6220629))
+* **ui:** make chat area stretch to fill the screen ([#1397](https://github.com/imartinez/privateGPT/issues/1397)) ([c71ae7c](https://github.com/imartinez/privateGPT/commit/c71ae7cee92463bbc5ea9c434eab9f99166e1363))
+* **UI:** Select file to Query or Delete + Delete ALL ([#1612](https://github.com/imartinez/privateGPT/issues/1612)) ([aa13afd](https://github.com/imartinez/privateGPT/commit/aa13afde07122f2ddda3942f630e5cadc7e4e1ee))
+
+
+### Bug Fixes
+
+* Adding an LLM param to fix broken generator from llamacpp ([#1519](https://github.com/imartinez/privateGPT/issues/1519)) ([869233f](https://github.com/imartinez/privateGPT/commit/869233f0e4f03dc23e5fae43cf7cb55350afdee9))
+* **deploy:** fix local and external dockerfiles ([fde2b94](https://github.com/imartinez/privateGPT/commit/fde2b942bc03688701ed563be6d7d597c75e4e4e))
+* **docker:** docker broken copy ([#1419](https://github.com/imartinez/privateGPT/issues/1419)) ([059f358](https://github.com/imartinez/privateGPT/commit/059f35840adbc3fb93d847d6decf6da32d08670c))
+* **docs:** Update quickstart doc and set version in pyproject.toml to 0.2.0 ([0a89d76](https://github.com/imartinez/privateGPT/commit/0a89d76cc5ed4371ffe8068858f23dfbb5e8cc37))
+* minor bug in chat stream output - python error being serialized ([#1449](https://github.com/imartinez/privateGPT/issues/1449)) ([6191bcd](https://github.com/imartinez/privateGPT/commit/6191bcdbd6e92b6f4d5995967dc196c9348c5954))
+* **settings:** correct yaml multiline string ([#1403](https://github.com/imartinez/privateGPT/issues/1403)) ([2564f8d](https://github.com/imartinez/privateGPT/commit/2564f8d2bb8c4332a6a0ab6d722a2ac15006b85f))
+* **tests:** load the test settings only when running tests ([d3acd85](https://github.com/imartinez/privateGPT/commit/d3acd85fe34030f8cfd7daf50b30c534087bdf2b))
+* **UI:** Updated ui.py. Frees up the CPU to not be bottlenecked. ([24fb80c](https://github.com/imartinez/privateGPT/commit/24fb80ca38f21910fe4fd81505d14960e9ed4faa))
+
+## [0.2.0](https://github.com/imartinez/privateGPT/compare/v0.1.0...v0.2.0) (2023-12-10)
+
+
+### Features
+
+* **llm:** drop default_system_prompt ([#1385](https://github.com/imartinez/privateGPT/issues/1385)) ([a3ed14c](https://github.com/imartinez/privateGPT/commit/a3ed14c58f77351dbd5f8f2d7868d1642a44f017))
+* **ui:** Allows User to Set System Prompt via "Additional Options" in Chat Interface ([#1353](https://github.com/imartinez/privateGPT/issues/1353)) ([145f3ec](https://github.com/imartinez/privateGPT/commit/145f3ec9f41c4def5abf4065a06fb0786e2d992a))
+
+## [0.1.0](https://github.com/imartinez/privateGPT/compare/v0.0.2...v0.1.0) (2023-11-30)
+
+
+### Features
+
+* Disable Gradio Analytics ([#1165](https://github.com/imartinez/privateGPT/issues/1165)) ([6583dc8](https://github.com/imartinez/privateGPT/commit/6583dc84c082773443fc3973b1cdf8095fa3fec3))
+* Drop loguru and use builtin `logging` ([#1133](https://github.com/imartinez/privateGPT/issues/1133)) ([64c5ae2](https://github.com/imartinez/privateGPT/commit/64c5ae214a9520151c9c2d52ece535867d799367))
+* enable resume download for hf_hub_download ([#1249](https://github.com/imartinez/privateGPT/issues/1249)) ([4197ada](https://github.com/imartinez/privateGPT/commit/4197ada6267c822f32c1d7ba2be6e7ce145a3404))
+* move torch and transformers to local group ([#1172](https://github.com/imartinez/privateGPT/issues/1172)) ([0d677e1](https://github.com/imartinez/privateGPT/commit/0d677e10b970aec222ec04837d0f08f1631b6d4a))
+* Qdrant support ([#1228](https://github.com/imartinez/privateGPT/issues/1228)) ([03d1ae6](https://github.com/imartinez/privateGPT/commit/03d1ae6d70dffdd2411f0d4e92f65080fff5a6e2))
+
+
+### Bug Fixes
+
+* Docker and sagemaker setup ([#1118](https://github.com/imartinez/privateGPT/issues/1118)) ([895588b](https://github.com/imartinez/privateGPT/commit/895588b82a06c2bc71a9e22fb840c7f6442a3b5b))
+* fix pytorch version to avoid wheel bug ([#1123](https://github.com/imartinez/privateGPT/issues/1123)) ([24cfddd](https://github.com/imartinez/privateGPT/commit/24cfddd60f74aadd2dade4c63f6012a2489938a1))
+* Remove global state ([#1216](https://github.com/imartinez/privateGPT/issues/1216)) ([022bd71](https://github.com/imartinez/privateGPT/commit/022bd718e3dfc197027b1e24fb97e5525b186db4))
+* sagemaker config and chat methods ([#1142](https://github.com/imartinez/privateGPT/issues/1142)) ([a517a58](https://github.com/imartinez/privateGPT/commit/a517a588c4927aa5c5c2a93e4f82a58f0599d251))
+* typo in README.md ([#1091](https://github.com/imartinez/privateGPT/issues/1091)) ([ba23443](https://github.com/imartinez/privateGPT/commit/ba23443a70d323cd4f9a242b33fd9dce1bacd2db))
+* Windows 11 failing to auto-delete tmp file ([#1260](https://github.com/imartinez/privateGPT/issues/1260)) ([0d52002](https://github.com/imartinez/privateGPT/commit/0d520026a3d5b08a9b8487be992d3095b21e710c))
+* Windows permission error on ingest service tmp files ([#1280](https://github.com/imartinez/privateGPT/issues/1280)) ([f1cbff0](https://github.com/imartinez/privateGPT/commit/f1cbff0fb7059432d9e71473cbdd039032dab60d))
+
+## [0.0.2](https://github.com/imartinez/privateGPT/compare/v0.0.1...v0.0.2) (2023-10-20)
+
+
+### Bug Fixes
+
+* chromadb max batch size ([#1087](https://github.com/imartinez/privateGPT/issues/1087)) ([f5a9bf4](https://github.com/imartinez/privateGPT/commit/f5a9bf4e374b2d4c76438cf8a97cccf222ec8e6f))
+
+## 0.0.1 (2023-10-20)
+
+### Miscellaneous Chores
+
+* Initial version ([490d93f](https://github.com/imartinez/privateGPT/commit/490d93fdc1977443c92f6c42e57a1c585aa59430))

CITATION.cff

@@ -0,0 +1,16 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: PrivateGPT
+message: >-
+  If you use this software, please cite it using the
+  metadata from this file.
+type: software
+authors:
+  - name: Zylon by PrivateGPT
+    address: [email protected]
+    website: 'https://www.zylon.ai/'
+repository-code: 'https://github.com/zylon-ai/private-gpt'
+license: Apache-2.0
+date-released: '2023-05-02'

Dockerfile.llamacpp-cpu

@@ -0,0 +1,62 @@
+### IMPORTANT, THIS IMAGE CAN ONLY BE RUN IN LINUX DOCKER
+### You will run into a segfault in mac
+FROM python:3.11.6-slim-bookworm as base
+
+# Install poetry
+RUN pip install pipx
+RUN python3 -m pipx ensurepath
+RUN pipx install poetry==1.8.3
+ENV PATH="/root/.local/bin:$PATH"
+ENV PATH=".venv/bin/:$PATH"
+
+# Dependencies to build llama-cpp
+RUN apt update && apt install -y \
+  libopenblas-dev\
+  ninja-build\
+  build-essential\
+  pkg-config\
+  wget
+
+# https://python-poetry.org/docs/configuration/#virtualenvsin-project
+ENV POETRY_VIRTUALENVS_IN_PROJECT=true
+
+FROM base as dependencies
+WORKDIR /home/worker/app
+COPY pyproject.toml poetry.lock ./
+
+ARG POETRY_EXTRAS="ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
+
+FROM base as app
+
+ENV PYTHONUNBUFFERED=1
+ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
+EXPOSE 8080
+
+# Prepare a non-root user
+# More info about how to configure UIDs and GIDs in Docker:
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=100
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
+WORKDIR /home/worker/app
+
+RUN chown worker /home/worker/app
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
+COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
+COPY --chown=worker private_gpt/ private_gpt
+COPY --chown=worker *.yaml ./
+COPY --chown=worker scripts/ scripts
+
+USER worker
+ENTRYPOINT python -m private_gpt

Dockerfile.ollama

@@ -0,0 +1,53 @@
+
+
+FROM python:3.11.6-slim-bookworm as base
+
+# Install poetry
+RUN pip install pipx
+RUN python3 -m pipx ensurepath
+RUN pipx install poetry==1.8.3
+ENV PATH="/root/.local/bin:$PATH"
+ENV PATH=".venv/bin/:$PATH"
+
+# https://python-poetry.org/docs/configuration/#virtualenvsin-project
+ENV POETRY_VIRTUALENVS_IN_PROJECT=true
+
+FROM base as dependencies
+WORKDIR /home/worker/app
+COPY pyproject.toml poetry.lock ./
+
+ARG POETRY_EXTRAS="ui vector-stores-qdrant llms-ollama embeddings-ollama"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
+
+FROM base as app
+ENV PYTHONUNBUFFERED=1
+ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
+EXPOSE 8080
+
+# Prepare a non-root user
+# More info about how to configure UIDs and GIDs in Docker:
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=100
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
+WORKDIR /home/worker/app
+
+RUN chown worker /home/worker/app
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
+COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
+COPY --chown=worker private_gpt/ private_gpt
+COPY --chown=worker *.yaml .
+COPY --chown=worker scripts/ scripts
+
+USER worker
+ENTRYPOINT python -m private_gpt

Dockerfile.openai

@@ -0,0 +1,53 @@
+
+
+FROM python:3.11.6-slim-bookworm as base
+
+# Install poetry
+RUN pip install pipx
+RUN python3 -m pipx ensurepath
+RUN pipx install poetry==1.8.3
+ENV PATH="/root/.local/bin:$PATH"
+ENV PATH=".venv/bin/:$PATH"
+
+# https://python-poetry.org/docs/configuration/#virtualenvsin-project
+ENV POETRY_VIRTUALENVS_IN_PROJECT=true
+
+FROM base as dependencies
+WORKDIR /home/worker/app
+COPY pyproject.toml poetry.lock ./
+
+ARG POETRY_EXTRAS="ui llms-openai embeddings-huggingface vector-stores-qdrant"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
+
+FROM base as app
+ENV PYTHONUNBUFFERED=1
+ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
+EXPOSE 8080
+
+# Prepare a non-root user
+# More info about how to configure UIDs and GIDs in Docker:
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=100
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
+WORKDIR /home/worker/app
+
+RUN chown worker /home/worker/app
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
+COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
+COPY --chown=worker private_gpt/ private_gpt
+COPY --chown=worker *.yaml .
+COPY --chown=worker scripts/ scripts
+
+USER worker
+ENTRYPOINT python -m private_gpt

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Makefile

@@ -0,0 +1,78 @@
+# Any args passed to the make script, use with $(call args, default_value)
+args = `arg="$(filter-out $@,$(MAKECMDGOALS))" && echo $${arg:-${1}}`
+
+########################################################################################################################
+# Quality checks
+########################################################################################################################
+
+test:
+	PYTHONPATH=. poetry run pytest tests
+
+test-coverage:
+	PYTHONPATH=. poetry run pytest tests --cov private_gpt --cov-report term --cov-report=html --cov-report xml --junit-xml=tests-results.xml
+
+black:
+	poetry run black . --check
+
+ruff:
+	poetry run ruff check private_gpt tests
+
+format:
+	poetry run black .
+	poetry run ruff check private_gpt tests --fix
+
+mypy:
+	poetry run mypy private_gpt
+
+check:
+	make format
+	make mypy
+
+########################################################################################################################
+# Run
+########################################################################################################################
+
+run:
+	poetry run python -m private_gpt
+
+dev-windows:
+	(set PGPT_PROFILES=local & poetry run python -m uvicorn private_gpt.main:app --reload --port 8001)
+
+dev:
+	PYTHONUNBUFFERED=1 PGPT_PROFILES=local poetry run python -m uvicorn private_gpt.main:app --reload --port 8001
+
+########################################################################################################################
+# Misc
+########################################################################################################################
+
+api-docs:
+	PGPT_PROFILES=mock poetry run python scripts/extract_openapi.py private_gpt.main:app --out fern/openapi/openapi.json
+
+ingest:
+	@poetry run python scripts/ingest_folder.py $(call args)
+
+stats:
+	poetry run python scripts/utils.py stats
+
+wipe:
+	poetry run python scripts/utils.py wipe
+
+setup:
+	poetry run python scripts/setup
+
+list:
+	@echo "Available commands:"
+	@echo "  test            : Run tests using pytest"
+	@echo "  test-coverage   : Run tests with coverage report"
+	@echo "  black           : Check code format with black"
+	@echo "  ruff            : Check code with ruff"
+	@echo "  format          : Format code with black and ruff"
+	@echo "  mypy            : Run mypy for type checking"
+	@echo "  check           : Run format and mypy commands"
+	@echo "  run             : Run the application"
+	@echo "  dev-windows     : Run the application in development mode on Windows"
+	@echo "  dev             : Run the application in development mode"
+	@echo "  api-docs        : Generate API documentation"
+	@echo "  ingest          : Ingest data using specified script"
+	@echo "  wipe            : Wipe data using specified script"
+	@echo "  setup           : Setup the application"

README-hydro.md

@@ -0,0 +1,154 @@
+# HidrogenGPT 📑
+
+![Gradio UI](/fern/docs/assets/ui-hidrogenGPT.jpg?raw=true)
+
+
+HidrogenGPT based on PrivateGPT, a production-ready AI project that allows you to ask questions about your documents using the power
+of Large Language Models (LLMs), even in scenarios without an Internet connection. 100% private, no data leaves your
+execution environment at any point.
+
+>[!TIP]
+> If you are looking for an **enterprise-ready, fully private AI workspace**
+> check out [Zylon's website](https://zylon.ai)  or [request a demo](https://cal.com/zylon/demo?source=pgpt-readme).
+> Crafted by the team behind PrivateGPT, Zylon is a best-in-class AI collaborative
+> workspace that can be easily deployed on-premise (data center, bare metal...) or in your private cloud (AWS, GCP, Azure...).
+
+The project provides an API offering all the primitives required to build private, context-aware AI applications.
+It follows and extends the [OpenAI API standard](https://openai.com/blog/openai-api),
+and supports both normal and streaming responses.
+
+The API is divided into two logical blocks:
+
+**High-level API**, which abstracts all the complexity of a RAG (Retrieval Augmented Generation)
+pipeline implementation:
+- Ingestion of documents: internally managing document parsing,
+splitting, metadata extraction, embedding generation and storage.
+- Chat & Completions using context from ingested documents:
+abstracting the retrieval of context, the prompt engineering and the response generation.
+
+**Low-level API**, which allows advanced users to implement their own complex pipelines:
+- Embeddings generation: based on a piece of text.
+- Contextual chunks retrieval: given a query, returns the most relevant chunks of text from the ingested documents.
+
+In addition to this, a working [Gradio UI](https://www.gradio.app/)
+client is provided to test the API, together with a set of useful tools such as bulk model
+download script, ingestion script, documents folder watch, etc.
+
+## 🎞️ Overview
+>[!WARNING]
+>  This README is not updated as frequently as the [documentation](https://docs.privategpt.dev/).
+>  Please check it out for the latest updates!
+
+### Motivation behind PrivateGPT
+Generative AI is a game changer for our society, but adoption in companies of all sizes and data-sensitive
+domains like healthcare or legal is limited by a clear concern: **privacy**.
+Not being able to ensure that your data is fully under your control when using third-party AI tools
+is a risk those industries cannot take.
+
+### Primordial version
+The first version of PrivateGPT was launched in May 2023 as a novel approach to address the privacy
+concerns by using LLMs in a complete offline way.
+
+That version, which rapidly became a go-to project for privacy-sensitive setups and served as the seed
+for thousands of local-focused generative AI projects, was the foundation of what PrivateGPT is becoming nowadays;
+thus a simpler and more educational implementation to understand the basic concepts required
+to build a fully local -and therefore, private- chatGPT-like tool.
+
+If you want to keep experimenting with it, we have saved it in the
+[primordial branch](https://github.com/zylon-ai/private-gpt/tree/primordial) of the project.
+
+> It is strongly recommended to do a clean clone and install of this new version of
+PrivateGPT if you come from the previous, primordial version.
+
+### Present and Future of PrivateGPT
+PrivateGPT is now evolving towards becoming a gateway to generative AI models and primitives, including
+completions, document ingestion, RAG pipelines and other low-level building blocks.
+We want to make it easier for any developer to build AI applications and experiences, as well as provide
+a suitable extensive architecture for the community to keep contributing.
+
+Stay tuned to our [releases](https://github.com/zylon-ai/private-gpt/releases) to check out all the new features and changes included.
+
+## 📄 Documentation
+Full documentation on installation, dependencies, configuration, running the server, deployment options,
+ingesting local documents, API details and UI features can be found here: https://docs.privategpt.dev/
+
+## 🧩 Architecture
+Conceptually, PrivateGPT is an API that wraps a RAG pipeline and exposes its
+primitives.
+* The API is built using [FastAPI](https://fastapi.tiangolo.com/) and follows
+  [OpenAI's API scheme](https://platform.openai.com/docs/api-reference).
+* The RAG pipeline is based on [LlamaIndex](https://www.llamaindex.ai/).
+
+The design of PrivateGPT allows to easily extend and adapt both the API and the
+RAG implementation. Some key architectural decisions are:
+* Dependency Injection, decoupling the different components and layers.
+* Usage of LlamaIndex abstractions such as `LLM`, `BaseEmbedding` or `VectorStore`,
+  making it immediate to change the actual implementations of those abstractions.
+* Simplicity, adding as few layers and new abstractions as possible.
+* Ready to use, providing a full implementation of the API and RAG
+  pipeline.
+
+Main building blocks:
+* APIs are defined in `private_gpt:server:<api>`. Each package contains an
+  `<api>_router.py` (FastAPI layer) and an `<api>_service.py` (the
+  service implementation). Each *Service* uses LlamaIndex base abstractions instead
+  of specific implementations,
+  decoupling the actual implementation from its usage.
+* Components are placed in
+  `private_gpt:components:<component>`. Each *Component* is in charge of providing
+  actual implementations to the base abstractions used in the Services - for example
+  `LLMComponent` is in charge of providing an actual implementation of an `LLM`
+  (for example `LlamaCPP` or `OpenAI`).
+
+## 💡 Contributing
+Contributions are welcomed! To ensure code quality we have enabled several format and
+typing checks, just run `make check` before committing to make sure your code is ok.
+Remember to test your code! You'll find a tests folder with helpers, and you can run
+tests using `make test` command.
+
+Don't know what to contribute? Here is the public 
+[Project Board](https://github.com/users/imartinez/projects/3) with several ideas. 
+
+Head over to Discord 
+#contributors channel and ask for write permissions on that GitHub project.
+
+## 💬 Community
+Join the conversation around PrivateGPT on our:
+- [Twitter (aka X)](https://twitter.com/PrivateGPT_AI)
+- [Discord](https://discord.gg/bK6mRVpErU)
+
+## 📖 Citation
+If you use PrivateGPT in a paper, check out the [Citation file](CITATION.cff) for the correct citation.  
+You can also use the "Cite this repository" button in this repo to get the citation in different formats.
+
+Here are a couple of examples:
+
+#### BibTeX
+```bibtex
+@software{Zylon_PrivateGPT_2023,
+author = {Zylon by PrivateGPT},
+license = {Apache-2.0},
+month = may,
+title = {{PrivateGPT}},
+url = {https://github.com/zylon-ai/private-gpt},
+year = {2023}
+}
+```
+
+#### APA
+```
+Zylon by PrivateGPT (2023). PrivateGPT [Computer software]. https://github.com/zylon-ai/private-gpt
+```
+
+## 🤗 Partners & Supporters
+PrivateGPT is actively supported by the teams behind:
+* [Qdrant](https://qdrant.tech/), providing the default vector database
+* [Fern](https://buildwithfern.com/), providing Documentation and SDKs
+* [LlamaIndex](https://www.llamaindex.ai/), providing the base RAG framework and abstractions
+
+This project has been strongly influenced and supported by other amazing projects like 
+[LangChain](https://github.com/hwchase17/langchain),
+[GPT4All](https://github.com/nomic-ai/gpt4all),
+[LlamaCpp](https://github.com/ggerganov/llama.cpp),
+[Chroma](https://www.trychroma.com/)
+and [SentenceTransformers](https://www.sbert.net/).

docker-compose.yaml

@@ -0,0 +1,116 @@
+services:
+
+  #-----------------------------------
+  #---- Private-GPT services ---------
+  #-----------------------------------
+
+  # Private-GPT service for the Ollama CPU and GPU modes
+  # This service builds from an external Dockerfile and runs the Ollama mode.
+  private-gpt-ollama:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-ollama  # x-release-please-version
+    build:
+      context: .
+      dockerfile: Dockerfile.ollama
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+    ports:
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: docker
+      PGPT_MODE: ollama
+      PGPT_EMBED_MODE: ollama
+      PGPT_OLLAMA_API_BASE: http://ollama:11434
+      HF_TOKEN: ${HF_TOKEN:-}
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+
+  # Private-GPT service for the local mode
+  # This service builds from a local Dockerfile and runs the application in local mode.
+  private-gpt-llamacpp-cpu:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-llamacpp-cpu # x-release-please-version
+    build:
+      context: .
+      dockerfile: Dockerfile.llamacpp-cpu
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+      - ./models/:/home/worker/app/models
+    entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
+    ports:
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: local
+      HF_TOKEN: ${HF_TOKEN}
+    profiles:
+      - llamacpp-cpu
+
+  #-----------------------------------
+  #---- Ollama services --------------
+  #-----------------------------------
+
+  # Traefik reverse proxy for the Ollama service
+  # This will route requests to the Ollama service based on the profile.
+  ollama:
+    image: traefik:v2.10
+    ports:
+      - "8081:8080"
+    command:
+      - "--providers.file.filename=/etc/router.yml"
+      - "--log.level=ERROR"
+      - "--api.insecure=true"
+      - "--providers.docker=true"
+      - "--providers.docker.exposedbydefault=false"
+      - "--entrypoints.web.address=:11434"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./.docker/router.yml:/etc/router.yml:ro
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+
+  # Ollama service for the CPU mode
+  ollama-cpu:
+    image: ollama/ollama:latest
+    volumes:
+      - ./models:/root/.ollama
+    profiles:
+      - ""
+      - ollama-cpu
+
+  # Ollama service for the CUDA mode
+  ollama-cuda:
+    image: ollama/ollama:latest
+    volumes:
+      - ./models:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    profiles:
+      - ollama-cuda
+  
+  openai:
+    image: 3x3cut0r/privategpt:latest
+    build:
+      context: .
+      dockerfile: Dockerfile.openai
+    container_name: privategpt
+    ports:
+      - 8080:8080/tcp
+    environment:
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      OPENAI_API_BASE: https://api.openai.com/v1
+      OPENAI_MODEL: gpt-4o-mini
+      OPENAI_TEMPERATURE: 0.5
+  

pyproject.toml

@@ -0,0 +1,204 @@
+[tool.poetry]
+name = "private-gpt"
+version = "0.6.2"
+description = "Private GPT"
+authors = ["Zylon <[email protected]>"]
+
+[tool.poetry.dependencies]
+python = ">=3.11,<3.12"
+# PrivateGPT
+fastapi = { extras = ["all"], version = "^0.111.0" }
+python-multipart = "^0.0.9"
+injector = "^0.21.0"
+pyyaml = "^6.0.1"
+watchdog = "^4.0.1"
+transformers = "^4.42.3"
+docx2txt = "^0.8"
+cryptography = "^3.1"
+# LlamaIndex core libs
+llama-index-core = "^0.10.52"
+llama-index-readers-file = "^0.1.27"
+# Optional LlamaIndex integration libs
+llama-index-llms-llama-cpp = {version = "^0.1.4", optional = true}
+llama-index-llms-openai = {version = "^0.1.25", optional = true}
+llama-index-llms-openai-like = {version ="^0.1.3", optional = true}
+llama-index-llms-ollama = {version ="^0.2.2", optional = true}
+llama-index-llms-azure-openai = {version ="^0.1.8", optional = true}
+llama-index-llms-gemini = {version ="^0.1.11", optional = true}
+llama-index-embeddings-ollama = {version ="^0.1.2", optional = true}
+llama-index-embeddings-huggingface = {version ="^0.2.2", optional = true}
+llama-index-embeddings-openai = {version ="^0.1.10", optional = true}
+llama-index-embeddings-azure-openai = {version ="^0.1.10", optional = true}
+llama-index-embeddings-gemini = {version ="^0.1.8", optional = true}
+llama-index-vector-stores-qdrant = {version ="^0.2.10", optional = true}
+llama-index-vector-stores-milvus = {version ="^0.1.20", optional = true}
+llama-index-vector-stores-chroma = {version ="^0.1.10", optional = true}
+llama-index-vector-stores-postgres = {version ="^0.1.11", optional = true}
+llama-index-vector-stores-clickhouse = {version ="^0.1.3", optional = true}
+llama-index-storage-docstore-postgres = {version ="^0.1.3", optional = true}
+llama-index-storage-index-store-postgres = {version ="^0.1.4", optional = true}
+# Postgres
+psycopg2-binary = {version ="^2.9.9", optional = true}
+asyncpg = {version="^0.29.0", optional = true}
+
+# ClickHouse
+clickhouse-connect = {version = "^0.7.15", optional = true}
+
+# Optional Sagemaker dependency
+boto3 = {version ="^1.34.139", optional = true}
+
+# Optional Qdrant client
+qdrant-client = {version ="^1.9.0", optional = true}
+
+# Optional Reranker dependencies
+torch = {version ="^2.3.1", optional = true}
+sentence-transformers = {version ="^3.0.1", optional = true}
+
+# Optional UI
+gradio = {version ="^4.37.2", optional = true}
+ffmpy = "0.4.0"
+
+# Optional Google Gemini dependency
+google-generativeai = {version ="^0.5.4", optional = true}
+
+# Optional Ollama client
+ollama = {version ="^0.3.0", optional = true}
+
+# Optional HF Transformers
+einops = {version = "^0.8.0", optional = true}
+retry-async = "^0.1.4"
+
+[tool.poetry.extras]
+ui = ["gradio", "ffmpy"]
+llms-llama-cpp = ["llama-index-llms-llama-cpp"]
+llms-openai = ["llama-index-llms-openai"]
+llms-openai-like = ["llama-index-llms-openai-like"]
+llms-ollama = ["llama-index-llms-ollama", "ollama"]
+llms-sagemaker = ["boto3"]
+llms-azopenai = ["llama-index-llms-azure-openai"]
+llms-gemini = ["llama-index-llms-gemini", "google-generativeai"]
+embeddings-ollama = ["llama-index-embeddings-ollama", "ollama"]
+embeddings-huggingface = ["llama-index-embeddings-huggingface", "einops"]
+embeddings-openai = ["llama-index-embeddings-openai"]
+embeddings-sagemaker = ["boto3"]
+embeddings-azopenai = ["llama-index-embeddings-azure-openai"]
+embeddings-gemini = ["llama-index-embeddings-gemini"]
+vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
+vector-stores-clickhouse = ["llama-index-vector-stores-clickhouse", "clickhouse_connect"]
+vector-stores-chroma = ["llama-index-vector-stores-chroma"]
+vector-stores-postgres = ["llama-index-vector-stores-postgres"]
+vector-stores-milvus = ["llama-index-vector-stores-milvus"]
+storage-nodestore-postgres = ["llama-index-storage-docstore-postgres","llama-index-storage-index-store-postgres","psycopg2-binary","asyncpg"]
+rerank-sentence-transformers = ["torch", "sentence-transformers"]
+
+[tool.poetry.group.dev.dependencies]
+black = "^22"
+mypy = "^1.2"
+pre-commit = "^2"
+pytest = "^7"
+pytest-cov = "^3"
+ruff = "^0"
+pytest-asyncio = "^0.21.1"
+types-pyyaml = "^6.0.12.12"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+# Packages configs
+
+## coverage
+
+[tool.coverage.run]
+branch = true
+
+[tool.coverage.report]
+skip_empty = true
+precision = 2
+
+## black
+
+[tool.black]
+target-version = ['py311']
+
+## ruff
+# Recommended ruff config for now, to be updated as we go along.
+[tool.ruff]
+target-version = 'py311'
+
+# See all rules at https://beta.ruff.rs/docs/rules/
+lint.select = [
+    "E", # pycodestyle
+    "W", # pycodestyle
+    "F", # Pyflakes
+    "B", # flake8-bugbear
+    "C4", # flake8-comprehensions
+    "D", # pydocstyle
+    "I", # isort
+    "SIM", # flake8-simplify
+    "TCH", # flake8-type-checking
+    "TID", # flake8-tidy-imports
+    "Q", # flake8-quotes
+    "UP", # pyupgrade
+    "PT", # flake8-pytest-style
+    "RUF", # Ruff-specific rules
+]
+
+lint.ignore = [
+    "E501", # "Line too long"
+    # -> line length already regulated by black
+    "PT011", # "pytest.raises() should specify expected exception"
+    # -> would imply to update tests every time you update exception message
+    "SIM102", # "Use a single `if` statement instead of nested `if` statements"
+    # -> too restrictive,
+    "D100",
+    "D101",
+    "D102",
+    "D103",
+    "D104",
+    "D105",
+    "D106",
+    "D107"
+    # -> "Missing docstring in public function too restrictive"
+]
+
+[tool.ruff.lint.pydocstyle]
+# Automatically disable rules that are incompatible with Google docstring convention
+convention = "google"
+
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 88
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[tool.ruff.lint.flake8-type-checking]
+strict = true
+runtime-evaluated-base-classes = ["pydantic.BaseModel"]
+# Pydantic needs to be able to evaluate types at runtime
+# see https://pypi.org/project/flake8-type-checking/ for flake8-type-checking documentation
+# see https://beta.ruff.rs/docs/settings/#flake8-type-checking-runtime-evaluated-base-classes for ruff documentation
+
+[tool.ruff.lint.per-file-ignores]
+# Allow missing docstrings for tests
+"tests/**/*.py" = ["D1"]
+
+## mypy
+
+[tool.mypy]
+python_version = "3.11"
+strict = true
+check_untyped_defs = false
+explicit_package_bases = true
+warn_unused_ignores = false
+exclude = ["tests"]
+
+[tool.mypy-llama-index]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+addopts = [
+    "--import-mode=importlib",
+]

settings-azopenai.yaml

@@ -0,0 +1,17 @@
+server:
+  env_name: ${APP_ENV:azopenai}
+
+llm:
+  mode: azopenai
+
+embedding:
+  mode: azopenai
+
+azopenai:
+  api_key: ${AZ_OPENAI_API_KEY:}
+  azure_endpoint: ${AZ_OPENAI_ENDPOINT:}
+  embedding_deployment_name: ${AZ_OPENAI_EMBEDDING_DEPLOYMENT_NAME:}
+  llm_deployment_name: ${AZ_OPENAI_LLM_DEPLOYMENT_NAME:}
+  api_version: "2023-05-15"
+  embedding_model: text-embedding-ada-002
+  llm_model: gpt-35-turbo

settings-docker.yaml

@@ -0,0 +1,37 @@
+server:
+  env_name: ${APP_ENV:prod}
+  port: ${PORT:8080}
+
+llm:
+  mode: ${PGPT_MODE:mock}
+
+embedding:
+  mode: ${PGPT_EMBED_MODE:mock}
+
+llamacpp:
+  llm_hf_repo_id: ${PGPT_HF_REPO_ID:lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF}
+  llm_hf_model_file: ${PGPT_HF_MODEL_FILE:Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf}
+
+huggingface:
+  embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:nomic-ai/nomic-embed-text-v1.5}
+
+sagemaker:
+  llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}
+  embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:}
+
+ollama:
+  llm_model: ${PGPT_OLLAMA_LLM_MODEL:llama3.1}
+  embedding_model: ${PGPT_OLLAMA_EMBEDDING_MODEL:nomic-embed-text}
+  api_base: ${PGPT_OLLAMA_API_BASE:http://ollama:11434}
+  embedding_api_base: ${PGPT_OLLAMA_EMBEDDING_API_BASE:http://ollama:11434}
+  tfs_z: ${PGPT_OLLAMA_TFS_Z:1.0}
+  top_k: ${PGPT_OLLAMA_TOP_K:40}
+  top_p: ${PGPT_OLLAMA_TOP_P:0.9}
+  repeat_last_n: ${PGPT_OLLAMA_REPEAT_LAST_N:64}
+  repeat_penalty: ${PGPT_OLLAMA_REPEAT_PENALTY:1.2}
+  request_timeout: ${PGPT_OLLAMA_REQUEST_TIMEOUT:600.0}
+  autopull_models: ${PGPT_OLLAMA_AUTOPULL_MODELS:true}
+
+ui:
+  enabled: true
+  path: /

settings-ollama.yaml

@@ -0,0 +1,30 @@
+server:
+  env_name: ${APP_ENV:ollama}
+
+llm:
+  mode: ollama
+  max_new_tokens: 512
+  context_window: 3900
+  temperature: 0.1     #The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1)
+
+embedding:
+  mode: ollama
+
+ollama:
+  llm_model: llama3.1
+  embedding_model: nomic-embed-text
+  api_base: http://localhost:11434
+  embedding_api_base: http://localhost:11434  # change if your embedding model runs on another ollama
+  keep_alive: 5m
+  tfs_z: 1.0              # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting.
+  top_k: 40               # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
+  top_p: 0.9              # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
+  repeat_last_n: 64       # Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
+  repeat_penalty: 1.2     # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
+  request_timeout: 12000.0  # Time elapsed until ollama times out the request. Default is 120s. Format is float.
+
+vectorstore:
+  database: qdrant
+
+qdrant:
+  path: local_data/private_gpt/qdrant

settings-openai.yaml

@@ -0,0 +1,14 @@
+server:
+  env_name: ${APP_ENV:openai}
+
+llm:
+  mode: openai
+
+embedding:
+  mode: huggingface
+
+openai:
+  api_base: https://api.openai.com/v1
+  api_key: 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
+  model: gpt-4o-mini
+  temperature: 0.5

settings.yaml

@@ -0,0 +1,156 @@
+# The default configuration file.
+# More information about configuration can be found in the documentation: https://docs.privategpt.dev/
+# Syntax in `private_pgt/settings/settings.py`
+server:
+  env_name: ${APP_ENV:prod}
+  port: ${PORT:8001}
+  cors:
+    enabled: true
+    allow_origins: ["*"]
+    allow_methods: ["*"]
+    allow_headers: ["*"]
+  auth:
+    enabled: false
+    # python -c 'import base64; print("Basic " + base64.b64encode("secret:key".encode()).decode())'
+    # 'secret' is the username and 'key' is the password for basic auth by default
+    # If the auth is enabled, this value must be set in the "Authorization" header of the request.
+    secret: "Basic c2VjcmV0OmtleQ=="
+
+data:
+  local_ingestion:
+    enabled: ${LOCAL_INGESTION_ENABLED:false}
+    allow_ingest_from: ["*"]
+  local_data_folder: local_data/private_gpt
+
+ui:
+  enabled: true
+  path: /
+  default_chat_system_prompt: >
+    You are a helpful, respectful and honest assistant. 
+    Always answer as helpfully as possible and follow ALL given instructions.
+    Do not speculate or make up information.
+    Do not reference any given instructions or context.
+  default_query_system_prompt: >
+    You can only answer questions strictly based on the information contained within the provided documents. 
+    Do not include any external knowledge or assumptions. 
+    If the relevant answer is not found in the documents, respond with: 'The answer is not found in the provided context.' 
+    Please ensure that all responses are concise and grounded solely in the provided material.
+      
+  default_summarization_system_prompt: >
+    Provide a comprehensive summary of the provided context information. 
+    The summary should cover all the key points and main ideas presented in
+    the original text, while also condensing the information into a concise 
+    and easy-to-understand format. Please ensure that the summary includes
+    relevant details and examples that support the main ideas, while avoiding 
+    any unnecessary information or repetition.
+  delete_file_button_enabled: true
+  delete_all_files_button_enabled: true
+    #You can only answer questions about the provided documents. 
+    #If you know the answer but it is not based in the provided context, don't provide 
+    #the answer, just state the answer is not in the context provided.
+
+llm:
+  mode: llamacpp
+  prompt_style: "llama3"
+  # Should be matching the selected model
+  max_new_tokens: 512
+  context_window: 3900
+  # Select your tokenizer. Llama-index tokenizer is the default.
+  # tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
+  temperature: 0.1      # The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1)
+
+rag:
+  similarity_top_k: 2
+  #This value controls how many "top" documents the RAG returns to use in the context.
+  #similarity_value: 0.45
+  #This value is disabled by default.  If you enable this settings, the RAG will only use articles that meet a certain percentage score.
+  rerank:
+    enabled: false
+    model: cross-encoder/ms-marco-MiniLM-L-2-v2
+    top_n: 1
+
+summarize:
+  use_async: true
+
+clickhouse:
+    host: localhost
+    port: 8443
+    username: admin
+    password: clickhouse
+    database: embeddings
+
+llamacpp:
+  llm_hf_repo_id: lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF
+  llm_hf_model_file: Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
+  tfs_z: 1.0            # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting
+  top_k: 40             # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
+  top_p: 1.0            # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
+  repeat_penalty: 1.1   # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
+
+embedding:
+  # Should be matching the value above in most cases
+  mode: huggingface
+  ingest_mode: simple
+  embed_dim: 768 # 768 is for nomic-ai/nomic-embed-text-v1.5
+
+huggingface:
+  embedding_hf_model_name: nomic-ai/nomic-embed-text-v1.5 #intfloat/multilingual-e5-large
+  access_token: ${HF_TOKEN:}
+  # Warning: Enabling this option will allow the model to download and execute code from the internet.
+  # Nomic AI requires this option to be enabled to use the model, be aware if you are using a different model.
+  trust_remote_code: true
+
+vectorstore:
+  database: qdrant
+
+nodestore:
+  database: simple
+
+milvus:
+  uri: local_data/private_gpt/milvus/milvus_local.db
+  collection_name: milvus_db
+  overwrite: false
+
+qdrant:
+  path: local_data/private_gpt/qdrant
+
+postgres:
+  host: localhost
+  port: 5432
+  database: postgres
+  user: postgres
+  password: postgres
+  schema_name: private_gpt
+
+sagemaker:
+  llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
+  embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479
+
+openai:
+  api_key: ${OPENAI_API_KEY:}
+  model: gpt-4o-mini
+  embedding_api_key: ${OPENAI_API_KEY:}
+  temperature: 0.5
+
+ollama:
+  llm_model: llama3.1
+  embedding_model: nomic-embed-text
+  api_base: http://localhost:11434
+  embedding_api_base: http://localhost:11434  # change if your embedding model runs on another ollama
+  keep_alive: 5m
+  request_timeout: 300.0
+  autopull_models: true
+
+azopenai:
+  api_key: ${AZ_OPENAI_API_KEY:}
+  azure_endpoint: ${AZ_OPENAI_ENDPOINT:}
+  embedding_deployment_name: ${AZ_OPENAI_EMBEDDING_DEPLOYMENT_NAME:}
+  llm_deployment_name: ${AZ_OPENAI_LLM_DEPLOYMENT_NAME:}
+  api_version: "2023-05-15"
+  embedding_model: text-embedding-ada-002
+  llm_model: gpt-35-turbo
+
+gemini:
+  api_key: ${GOOGLE_API_KEY:}
+  model: models/gemini-pro
+  embedding_model: models/embedding-001

version.txt

@@ -0,0 +1 @@
+0.6.2