diff --git a/README.md b/README.md
index 49bea93..be4eaf5 100644
--- a/README.md
+++ b/README.md
@@ -71,12 +71,18 @@ Upon app startup, OpenAI-compatible embedding API will be available at:
 
 Check the docs here: <http://172.16.3.101:5001/docs>
 
-#### llamacpp
+#### Download llm model (must have for servis llm to work !!!)
 
-Download models (this can take >1h):
+Download model (size of file 3.6GB ):
 
 ```sh
-wget https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/resolve/main/sheep-duck-llama-2-70b-v1.1.Q4_K_S.gguf
+curl -o ./llm/models/llama-2-7b.Q3_K_L.gguf -L https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q3_K_L.gguf
+```
+
+or
+
+```sh
+wget -P ./llm/models/llama-2-7b.Q3_K_L.gguf https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q3_K_L.gguf
 ```
 
 #### Starting app
diff --git a/docker-compose.yml b/docker-compose.yml
index d6df695..5a05b3e 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,6 +1,6 @@
 services:
   discord-bot:
-    profiles: ["dev","prod"]
+    profiles: [ "dev", "prod" ]
     build: ./discord_bot
     env_file: .env
 
@@ -16,7 +16,7 @@ services:
       - .env
 
   api:
-    profiles: ["dev","prod"]
+    profiles: [ "dev", "prod" ]
     build:
       context: ./api/
     env_file:
@@ -27,3 +27,12 @@ services:
       - "8000:8000"
     depends_on:
       - db
+
+  llm:
+    profiles: [ "dev", "prod" ]
+    build:
+      context: ./llm/
+    volumes:
+      - ./llm/models:/models
+    ports:
+      - "9000:9000"
diff --git a/llm/.gitignore b/llm/.gitignore
new file mode 100644
index 0000000..6abb9a4
--- /dev/null
+++ b/llm/.gitignore
@@ -0,0 +1,5 @@
+models/
+*.ipynb
+llama-cpp-python/
+.pytest_cache/
+__pycache__/
diff --git a/llm/Dockerfile b/llm/Dockerfile
new file mode 100644
index 0000000..b4b8395
--- /dev/null
+++ b/llm/Dockerfile
@@ -0,0 +1,28 @@
+FROM python:3.11-buster as builder
+
+RUN pip install poetry==1.6.1
+RUN apt-get update && apt-get install -y git
+RUN git clone --recurse-submodules https://github.com/abetlen/llama-cpp-python.git
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=1 \
+    POETRY_CACHE_DIR=/tmp/poetry_cachee
+
+WORKDIR /app
+
+COPY pyproject.toml poetry.lock ./
+RUN touch README.md
+
+RUN --mount=type=cache,target=$POETRY_CACHE_DIR poetry install 
+
+FROM python:3.11-slim-buster as runtime
+
+ENV VIRTUAL_ENV=/app/.venv \
+    PATH="/app/.venv/bin:$PATH"
+
+COPY --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python[server]
+
+ENTRYPOINT ["python3", "-m", "llama_cpp.server", "--host", "0.0.0.0", "--port", "9000", "--model", "models/llama-2-7b.Q3_K_L.gguf", "--n_gpu_layers", "9999999"]
diff --git a/llm/poetry.lock b/llm/poetry.lock
new file mode 100644
index 0000000..129213d
--- /dev/null
+++ b/llm/poetry.lock
@@ -0,0 +1,679 @@
+[[package]]
+name = "aiohttp"
+version = "3.9.3"
+description = "Async http client/server framework (asyncio)"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+aiosignal = ">=1.1.2"
+attrs = ">=17.3.0"
+frozenlist = ">=1.1.1"
+multidict = ">=4.5,<7.0"
+yarl = ">=1.0,<2.0"
+
+[package.extras]
+speedups = ["brotlicffi", "brotli", "aiodns"]
+
+[[package]]
+name = "aiosignal"
+version = "1.3.1"
+description = "aiosignal: a list of registered asynchronous callbacks"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+frozenlist = ">=1.1.0"
+
+[[package]]
+name = "annotated-types"
+version = "0.6.0"
+description = "Reusable constraint types to use with typing.Annotated"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "anyio"
+version = "4.3.0"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+idna = ">=2.8"
+sniffio = ">=1.1"
+
+[package.extras]
+doc = ["packaging", "Sphinx (>=7)", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
+test = ["anyio", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
+trio = ["trio (>=0.23)"]
+
+[[package]]
+name = "attrs"
+version = "23.2.0"
+description = "Classes Without Boilerplate"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+cov = ["attrs", "coverage[toml] (>=5.3)"]
+dev = ["attrs", "pre-commit"]
+docs = ["furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier", "zope-interface"]
+tests = ["attrs", "zope-interface"]
+tests-mypy = ["mypy (>=1.6)", "pytest-mypy-plugins"]
+tests-no-zope = ["attrs", "cloudpickle", "hypothesis", "pympler", "pytest-xdist", "pytest (>=4.3.0)"]
+
+[[package]]
+name = "certifi"
+version = "2024.2.2"
+description = "Python package for providing Mozilla's CA Bundle."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "charset-normalizer"
+version = "3.3.2"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+
+[[package]]
+name = "click"
+version = "8.1.7"
+description = "Composable command line interface toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+
+[[package]]
+name = "dataclasses-json"
+version = "0.6.4"
+description = "Easily serialize dataclasses to and from JSON."
+category = "main"
+optional = false
+python-versions = ">=3.7,<4.0"
+
+[package.dependencies]
+marshmallow = ">=3.18.0,<4.0.0"
+typing-inspect = ">=0.4.0,<1"
+
+[[package]]
+name = "diskcache"
+version = "5.6.3"
+description = "Disk Cache -- Disk and file backed persistent cache."
+category = "main"
+optional = false
+python-versions = ">=3"
+
+[[package]]
+name = "distro"
+version = "1.9.0"
+description = "Distro - an OS platform information API"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "frozenlist"
+version = "1.4.1"
+description = "A list-like structure which implements collections.abc.MutableSequence"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "greenlet"
+version = "3.0.3"
+description = "Lightweight in-process concurrent programming"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+docs = ["sphinx", "furo"]
+test = ["objgraph", "psutil"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "httpcore"
+version = "1.0.4"
+description = "A minimal low-level HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+certifi = "*"
+h11 = ">=0.13,<0.15"
+
+[package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+trio = ["trio (>=0.22.0,<0.25.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.27.0"
+description = "The next generation HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+anyio = "*"
+certifi = "*"
+httpcore = ">=1.0.0,<2.0.0"
+idna = "*"
+sniffio = "*"
+
+[package.extras]
+brotli = ["brotli", "brotlicffi"]
+cli = ["click (>=8.0.0,<9.0.0)", "pygments (>=2.0.0,<3.0.0)", "rich (>=10,<14)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+
+[[package]]
+name = "idna"
+version = "3.6"
+description = "Internationalized Domain Names in Applications (IDNA)"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "jinja2"
+version = "3.1.3"
+description = "A very fast and expressive template engine."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "jsonpatch"
+version = "1.33"
+description = "Apply JSON-Patches (RFC 6902)"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
+
+[package.dependencies]
+jsonpointer = ">=1.9"
+
+[[package]]
+name = "jsonpointer"
+version = "2.4"
+description = "Identify specific nodes in a JSON document (RFC 6901)"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
+
+[[package]]
+name = "langchain"
+version = "0.1.9"
+description = "Building applications with LLMs through composability"
+category = "main"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+
+[package.dependencies]
+aiohttp = ">=3.8.3,<4.0.0"
+dataclasses-json = ">=0.5.7,<0.7"
+jsonpatch = ">=1.33,<2.0"
+langchain-community = ">=0.0.21,<0.1"
+langchain-core = ">=0.1.26,<0.2"
+langsmith = ">=0.1.0,<0.2.0"
+numpy = ">=1,<2"
+pydantic = ">=1,<3"
+PyYAML = ">=5.3"
+requests = ">=2,<3"
+SQLAlchemy = ">=1.4,<3"
+tenacity = ">=8.1.0,<9.0.0"
+
+[package.extras]
+extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "cohere (>=4,<5)", "couchbase (>=4.1.9,<5.0.0)", "dashvector (>=1.0.1,<2.0.0)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "hologres-vector (>=0.0.6,<0.0.7)", "html2text (>=2020.1.16,<2021.0.0)", "javelin-sdk (>=0.1.8,<0.2.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "langchain-openai (>=0.0.2,<0.1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "msal (>=1.25.0,<2.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "praw (>=7.7.1,<8.0.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "rdflib (==7.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
+azure = ["azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-textanalytics (>=5.3.0,<6.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-core (>=1.26.4,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "azure-search-documents (==11.4.0b8)", "openai (<2)"]
+text-helpers = ["chardet (>=5.1.0,<6.0.0)"]
+llms = ["clarifai (>=9.1.0)", "cohere (>=4,<5)", "huggingface_hub (>=0,<1)", "manifest-ml (>=0.0.1,<0.0.2)", "nlpcloud (>=1,<2)", "openai (<2)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
+clarifai = ["clarifai (>=9.1.0)"]
+cohere = ["cohere (>=4,<5)"]
+docarray = ["docarray[hnswlib] (>=0.32.0,<0.33.0)"]
+javascript = ["esprima (>=4.0.1,<5.0.0)"]
+openai = ["openai (<2)", "tiktoken (>=0.3.2,<0.6.0)"]
+qdrant = ["qdrant-client (>=1.3.1,<2.0.0)"]
+embeddings = ["sentence-transformers (>=2,<3)"]
+cli = ["typer (>=0.9.0,<0.10.0)"]
+
+[[package]]
+name = "langchain-community"
+version = "0.0.24"
+description = "Community contributed LangChain integrations."
+category = "main"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+
+[package.dependencies]
+aiohttp = ">=3.8.3,<4.0.0"
+dataclasses-json = ">=0.5.7,<0.7"
+langchain-core = ">=0.1.26,<0.2"
+langsmith = ">=0.1.0,<0.2.0"
+numpy = ">=1,<2"
+PyYAML = ">=5.3"
+requests = ">=2,<3"
+SQLAlchemy = ">=1.4,<3"
+tenacity = ">=8.1.0,<9.0.0"
+
+[package.extras]
+extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "azure-ai-documentintelligence (>=1.0.0b1,<2.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "cohere (>=4,<5)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "elasticsearch (>=8.12.0,<9.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "gradientai (>=1.4.0,<2.0.0)", "hdbcli (>=2.19.21,<3.0.0)", "hologres-vector (>=0.0.6,<0.0.7)", "html2text (>=2020.1.16,<2021.0.0)", "httpx (>=0.24.1,<0.25.0)", "javelin-sdk (>=0.1.8,<0.2.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "msal (>=1.25.0,<2.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "nvidia-riva-client (>=2.14.0,<3.0.0)", "oci (>=2.119.1,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "oracle-ads (>=2.9.1,<3.0.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "praw (>=7.7.1,<8.0.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "rdflib (==7.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "tree-sitter (>=0.20.2,<0.21.0)", "tree-sitter-languages (>=1.8.0,<2.0.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)", "zhipuai (>=1.0.7,<2.0.0)"]
+cli = ["typer (>=0.9.0,<0.10.0)"]
+
+[[package]]
+name = "langchain-core"
+version = "0.1.26"
+description = "Building applications with LLMs through composability"
+category = "main"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+
+[package.dependencies]
+anyio = ">=3,<5"
+jsonpatch = ">=1.33,<2.0"
+langsmith = ">=0.1.0,<0.2.0"
+packaging = ">=23.2,<24.0"
+pydantic = ">=1,<3"
+PyYAML = ">=5.3"
+requests = ">=2,<3"
+tenacity = ">=8.1.0,<9.0.0"
+
+[package.extras]
+extended-testing = ["jinja2 (>=3,<4)"]
+
+[[package]]
+name = "langsmith"
+version = "0.1.7"
+description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
+category = "main"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+
+[package.dependencies]
+orjson = ">=3.9.14,<4.0.0"
+pydantic = ">=1,<3"
+requests = ">=2,<3"
+
+[[package]]
+name = "llama-cpp-python"
+version = "0.2.50"
+description = "Python bindings for the llama.cpp library"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+diskcache = ">=5.6.1"
+jinja2 = ">=2.11.3"
+numpy = ">=1.20.0"
+typing-extensions = ">=4.5.0"
+
+[package.extras]
+server = ["uvicorn (>=0.22.0)", "fastapi (>=0.100.0)", "pydantic-settings (>=2.0.1)", "sse-starlette (>=1.6.1)", "starlette-context (>=0.3.6,<0.4)"]
+test = ["pytest (>=7.4.0)", "httpx (>=0.24.1)", "scipy (>=1.10)"]
+dev = ["black (>=23.3.0)", "twine (>=4.0.2)", "mkdocs (>=1.4.3)", "mkdocstrings[python] (>=0.22.0)", "mkdocs-material (>=9.1.18)", "pytest (>=7.4.0)", "httpx (>=0.24.1)"]
+all = ["llama-cpp-python"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.5"
+description = "Safely add untrusted strings to HTML/XML markup."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "marshmallow"
+version = "3.20.2"
+description = "A lightweight library for converting complex datatypes to and from native Python datatypes."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+packaging = ">=17.0"
+
+[package.extras]
+dev = ["pytest", "pytz", "simplejson", "pre-commit (>=2.4,<4.0)", "tox"]
+docs = ["sphinx (==7.2.6)", "sphinx-issues (==3.0.1)", "alabaster (==0.7.15)", "sphinx-version-warning (==1.1.2)", "autodocsumm (==0.2.12)"]
+lint = ["pre-commit (>=2.4,<4.0)"]
+tests = ["pytest", "pytz", "simplejson"]
+
+[[package]]
+name = "multidict"
+version = "6.0.5"
+description = "multidict implementation"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "mypy-extensions"
+version = "1.0.0"
+description = "Type system extensions for programs checked with the mypy type checker."
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "numpy"
+version = "1.26.4"
+description = "Fundamental package for array computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.9"
+
+[[package]]
+name = "openai"
+version = "1.12.0"
+description = "The official Python library for the openai API"
+category = "main"
+optional = false
+python-versions = ">=3.7.1"
+
+[package.dependencies]
+anyio = ">=3.5.0,<5"
+distro = ">=1.7.0,<2"
+httpx = ">=0.23.0,<1"
+pydantic = ">=1.9.0,<3"
+sniffio = "*"
+tqdm = ">4"
+typing-extensions = ">=4.7,<5"
+
+[package.extras]
+datalib = ["numpy (>=1)", "pandas-stubs (>=1.1.0.11)", "pandas (>=1.2.3)"]
+
+[[package]]
+name = "orjson"
+version = "3.9.15"
+description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "packaging"
+version = "23.2"
+description = "Core utilities for Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "pydantic"
+version = "2.6.2"
+description = "Data validation using Python type hints"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+annotated-types = ">=0.4.0"
+pydantic-core = "2.16.3"
+typing-extensions = ">=4.6.1"
+
+[package.extras]
+email = ["email-validator (>=2.0.0)"]
+
+[[package]]
+name = "pydantic-core"
+version = "2.16.3"
+description = ""
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
+
+[[package]]
+name = "pyyaml"
+version = "6.0.1"
+description = "YAML parser and emitter for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "requests"
+version = "2.31.0"
+description = "Python HTTP for Humans."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "sniffio"
+version = "1.3.0"
+description = "Sniff out which async library your code is running under"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "sqlalchemy"
+version = "2.0.27"
+description = "Database Abstraction Library"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+greenlet = {version = "!=0.4.17", markers = "platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\""}
+typing-extensions = ">=4.6.0"
+
+[package.extras]
+asyncio = ["greenlet (!=0.4.17)"]
+mypy = ["mypy (>=0.910)"]
+mssql = ["pyodbc"]
+mssql-pymssql = ["pymssql"]
+mssql-pyodbc = ["pyodbc"]
+mysql = ["mysqlclient (>=1.4.0)"]
+mysql-connector = ["mysql-connector-python"]
+mariadb-connector = ["mariadb (>=1.0.1,!=1.1.2,!=1.1.5)"]
+oracle = ["cx_oracle (>=8)"]
+oracle-oracledb = ["oracledb (>=1.0.1)"]
+postgresql = ["psycopg2 (>=2.7)"]
+postgresql-pg8000 = ["pg8000 (>=1.29.1)"]
+postgresql-asyncpg = ["greenlet (!=0.4.17)", "asyncpg"]
+postgresql-psycopg2binary = ["psycopg2-binary"]
+postgresql-psycopg2cffi = ["psycopg2cffi"]
+postgresql-psycopg = ["psycopg (>=3.0.7)"]
+postgresql-psycopgbinary = ["psycopg[binary] (>=3.0.7)"]
+pymysql = ["pymysql"]
+aiomysql = ["greenlet (!=0.4.17)", "aiomysql (>=0.2.0)"]
+aioodbc = ["greenlet (!=0.4.17)", "aioodbc"]
+asyncmy = ["greenlet (!=0.4.17)", "asyncmy (>=0.2.3,!=0.2.4,!=0.2.6)"]
+aiosqlite = ["greenlet (!=0.4.17)", "aiosqlite", "typing_extensions (!=3.10.0.1)"]
+sqlcipher = ["sqlcipher3-binary"]
+
+[[package]]
+name = "tenacity"
+version = "8.2.3"
+description = "Retry code until it succeeds"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+doc = ["reno", "sphinx", "tornado (>=4.5)"]
+
+[[package]]
+name = "tqdm"
+version = "4.66.2"
+description = "Fast, Extensible Progress Meter"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
+name = "typing-extensions"
+version = "4.9.0"
+description = "Backported and Experimental Type Hints for Python 3.8+"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "typing-inspect"
+version = "0.9.0"
+description = "Runtime inspection utilities for typing module."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+mypy-extensions = ">=0.3.0"
+typing-extensions = ">=3.7.4"
+
+[[package]]
+name = "urllib3"
+version = "2.2.1"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.extras]
+brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+h2 = ["h2 (>=4,<5)"]
+socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
+zstd = ["zstandard (>=0.18.0)"]
+
+[[package]]
+name = "uvicorn"
+version = "0.26.0"
+description = "The lightning-fast ASGI server."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+click = ">=7.0"
+h11 = ">=0.8"
+
+[package.extras]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+
+[[package]]
+name = "yarl"
+version = "1.9.4"
+description = "Yet another URL library"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+idna = ">=2.0"
+multidict = ">=4.0"
+
+[metadata]
+lock-version = "1.1"
+python-versions = "^3.11"
+content-hash = "a63919082a5d2a4a0c84428e6d74caa9e94b6d05d631d75a6089d4245788c890"
+
+[metadata.files]
+aiohttp = []
+aiosignal = []
+annotated-types = []
+anyio = []
+attrs = []
+certifi = []
+charset-normalizer = []
+click = []
+colorama = []
+dataclasses-json = []
+diskcache = []
+distro = []
+frozenlist = []
+greenlet = []
+h11 = []
+httpcore = []
+httpx = []
+idna = []
+jinja2 = []
+jsonpatch = []
+jsonpointer = []
+langchain = []
+langchain-community = []
+langchain-core = []
+langsmith = []
+llama-cpp-python = []
+markupsafe = []
+marshmallow = []
+multidict = []
+mypy-extensions = []
+numpy = []
+openai = []
+orjson = []
+packaging = []
+pydantic = []
+pydantic-core = []
+pyyaml = []
+requests = []
+sniffio = []
+sqlalchemy = []
+tenacity = []
+tqdm = []
+typing-extensions = []
+typing-inspect = []
+urllib3 = []
+uvicorn = []
+yarl = []
diff --git a/llm/pyproject.toml b/llm/pyproject.toml
new file mode 100644
index 0000000..80f0582
--- /dev/null
+++ b/llm/pyproject.toml
@@ -0,0 +1,24 @@
+[tool.poetry]
+name = "llm"
+version = "0.1.0"
+description = ""
+authors = ["Kleczyk <mailnasyff@gmail.com>"]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+openai = "^1.8.0"
+langchain = "^0.1.1"
+llama-cpp-python = "^0.2.29"
+uvicorn = "^0.26.0"
+
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+markers = [
+    "llm",
+]
diff --git a/llm/test/test_llm.py b/llm/test/test_llm.py
new file mode 100644
index 0000000..9762769
--- /dev/null
+++ b/llm/test/test_llm.py
@@ -0,0 +1,20 @@
+# test_llm.py
+
+import pytest
+import requests
+
+
+@pytest.mark.llm
+def test_llm_response():
+    url = "http://0.0.0.0:9000/v1/completions"
+
+    prompt = "co jest stolicą polski?"
+    stop_signs = ("\n", "###")
+    data = {"prompt": prompt, "stop": stop_signs}
+
+    response = requests.post(url, json=data)
+
+    resp_body = response.json()
+    assert response.status_code == 200
+    assert "choices" in resp_body
+    assert "text" in resp_body["choices"][0]
diff --git a/llm/test/test_promt.py b/llm/test/test_promt.py
new file mode 100644
index 0000000..dbc2ccb
--- /dev/null
+++ b/llm/test/test_promt.py
@@ -0,0 +1,26 @@
+import requests
+import json
+
+def query_local_openai_api(prompt, stop_signs):
+    url = 'http://127.0.0.1:9000/v1/completions'
+    headers = {'Content-Type': 'application/json'}
+    data = {
+        'prompt': prompt,
+        'stop': stop_signs
+    }
+
+    response = requests.post(url, headers=headers, data=json.dumps(data))
+    
+    if response.status_code == 200:
+        return response.json()
+    else:
+        return response.text
+
+# Prompt and stop_signs
+prompt = "\n\n### Instructions:\n jaka jest stolica polski\n\n### Response:\n"
+stop_signs = ["\n", "###"]
+
+# Query local API
+result = query_local_openai_api(prompt, stop_signs)
+
+print(result['choices'][0]['text'])