initial commit

Dockerfile

@@ -0,0 +1,21 @@
+# syntax=docker/dockerfile:1.0.0-experimental
+FROM taprosoft/kotaemon:v1.0 as base_image
+ARG APP_DATA_DIR=/home/ubuntu/lib-knowledgehub/kotaemon/
+
+RUN apt update -qqy \
+  && apt install -y unzip \
+  && \
+  apt-get clean && \
+  apt-get autoremove
+
+WORKDIR /app
+RUN --mount=type=ssh mkdir -p ${APP_DATA_DIR}
+
+COPY ktem_app_data.zip ${APP_DATA_DIR}
+COPY flowsettings.py /app
+
+RUN --mount=type=ssh cd ${APP_DATA_DIR} \
+  && unzip ktem_app_data.zip \
+  && rm ktem_app_data.zip
+
+ENTRYPOINT ["python", "app.py"]

flowsettings.py

@@ -0,0 +1,243 @@
+import os
+from importlib.metadata import version
+from inspect import currentframe, getframeinfo
+from pathlib import Path
+
+from decouple import config
+from theflow.settings.default import *  # noqa
+
+cur_frame = currentframe()
+if cur_frame is None:
+    raise ValueError("Cannot get the current frame.")
+this_file = getframeinfo(cur_frame).filename
+this_dir = Path(this_file).parent
+
+# change this if your app use a different name
+KH_PACKAGE_NAME = "kotaemon_app"
+
+KH_APP_VERSION = config("KH_APP_VERSION", "local")
+if not KH_APP_VERSION:
+    try:
+        # Caution: This might produce the wrong version
+        # https://stackoverflow.com/a/59533071
+        KH_APP_VERSION = version(KH_PACKAGE_NAME)
+    except Exception as e:
+        print(f"Failed to get app version: {e}")
+
+# App can be ran from anywhere and it's not trivial to decide where to store app data.
+# So let's use the same directory as the flowsetting.py file.
+# KH_APP_DATA_DIR = this_dir / "ktem_app_data"
+
+# override app data dir to fit preview data
+KH_APP_DATA_DIR = Path("/home/ubuntu/lib-knowledgehub/kotaemon/ktem_app_data")
+KH_APP_DATA_DIR.mkdir(parents=True, exist_ok=True)
+
+# User data directory
+KH_USER_DATA_DIR = KH_APP_DATA_DIR / "user_data"
+KH_USER_DATA_DIR.mkdir(parents=True, exist_ok=True)
+
+# markdowm output directory
+KH_MARKDOWN_OUTPUT_DIR = KH_APP_DATA_DIR / "markdown_cache_dir"
+KH_MARKDOWN_OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+# chunks output directory
+KH_CHUNKS_OUTPUT_DIR = KH_APP_DATA_DIR / "chunks_cache_dir"
+KH_CHUNKS_OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+# zip output directory
+KH_ZIP_OUTPUT_DIR = KH_APP_DATA_DIR / "zip_cache_dir"
+KH_ZIP_OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+# zip input directory
+KH_ZIP_INPUT_DIR = KH_APP_DATA_DIR / "zip_cache_dir_in"
+KH_ZIP_INPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+# HF models can be big, let's store them in the app data directory so that it's easier
+# for users to manage their storage.
+# ref: https://huggingface.co/docs/huggingface_hub/en/guides/manage-cache
+os.environ["HF_HOME"] = str(KH_APP_DATA_DIR / "huggingface")
+os.environ["HF_HUB_CACHE"] = str(KH_APP_DATA_DIR / "huggingface")
+
+# doc directory
+KH_DOC_DIR = this_dir / "docs"
+
+KH_MODE = "dev"
+KH_FEATURE_USER_MANAGEMENT = False
+KH_USER_CAN_SEE_PUBLIC = None
+KH_FEATURE_USER_MANAGEMENT_ADMIN = str(
+    config("KH_FEATURE_USER_MANAGEMENT_ADMIN", default="admin")
+)
+KH_FEATURE_USER_MANAGEMENT_PASSWORD = str(
+    config("KH_FEATURE_USER_MANAGEMENT_PASSWORD", default="admin")
+)
+KH_ENABLE_ALEMBIC = False
+KH_DATABASE = f"sqlite:///file:{KH_USER_DATA_DIR / 'sql.db?mode=ro&uri=true'}"
+KH_FILESTORAGE_PATH = str(KH_USER_DATA_DIR / "files")
+
+KH_DOCSTORE = {
+    # "__type__": "kotaemon.storages.ElasticsearchDocumentStore",
+    # "__type__": "kotaemon.storages.SimpleFileDocumentStore",
+    "__type__": "kotaemon.storages.LanceDBDocumentStore",
+    "path": str(KH_USER_DATA_DIR / "docstore"),
+}
+KH_VECTORSTORE = {
+    # "__type__": "kotaemon.storages.LanceDBVectorStore",
+    "__type__": "kotaemon.storages.ChromaVectorStore",
+    "path": str(KH_USER_DATA_DIR / "vectorstore"),
+}
+KH_LLMS = {}
+KH_EMBEDDINGS = {}
+
+# populate options from config
+if config("AZURE_OPENAI_API_KEY", default="") and config(
+    "AZURE_OPENAI_ENDPOINT", default=""
+):
+    if config("AZURE_OPENAI_CHAT_DEPLOYMENT", default=""):
+        KH_LLMS["azure"] = {
+            "spec": {
+                "__type__": "kotaemon.llms.AzureChatOpenAI",
+                "temperature": 0,
+                "azure_endpoint": config("AZURE_OPENAI_ENDPOINT", default=""),
+                "api_key": config("AZURE_OPENAI_API_KEY", default=""),
+                "api_version": config("OPENAI_API_VERSION", default="")
+                or "2024-02-15-preview",
+                "azure_deployment": config("AZURE_OPENAI_CHAT_DEPLOYMENT", default=""),
+                "timeout": 20,
+            },
+            "default": False,
+        }
+    if config("AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT", default=""):
+        KH_EMBEDDINGS["azure"] = {
+            "spec": {
+                "__type__": "kotaemon.embeddings.AzureOpenAIEmbeddings",
+                "azure_endpoint": config("AZURE_OPENAI_ENDPOINT", default=""),
+                "api_key": config("AZURE_OPENAI_API_KEY", default=""),
+                "api_version": config("OPENAI_API_VERSION", default="")
+                or "2024-02-15-preview",
+                "azure_deployment": config(
+                    "AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT", default=""
+                ),
+                "timeout": 10,
+            },
+            "default": False,
+        }
+
+if config("OPENAI_API_KEY", default=""):
+    KH_LLMS["openai"] = {
+        "spec": {
+            "__type__": "kotaemon.llms.ChatOpenAI",
+            "temperature": 0,
+            "base_url": config("OPENAI_API_BASE", default="")
+            or "https://api.openai.com/v1",
+            "api_key": config("OPENAI_API_KEY", default=""),
+            "model": config("OPENAI_CHAT_MODEL", default="gpt-3.5-turbo"),
+            "timeout": 20,
+        },
+        "default": True,
+    }
+    KH_EMBEDDINGS["openai"] = {
+        "spec": {
+            "__type__": "kotaemon.embeddings.OpenAIEmbeddings",
+            "base_url": config("OPENAI_API_BASE", default="https://api.openai.com/v1"),
+            "api_key": config("OPENAI_API_KEY", default=""),
+            "model": config(
+                "OPENAI_EMBEDDINGS_MODEL", default="text-embedding-ada-002"
+            ),
+            "timeout": 10,
+            "context_length": 8191,
+        },
+        "default": True,
+    }
+
+if config("LOCAL_MODEL", default=""):
+    KH_LLMS["ollama"] = {
+        "spec": {
+            "__type__": "kotaemon.llms.ChatOpenAI",
+            "base_url": "http://localhost:11434/v1/",
+            "model": config("LOCAL_MODEL", default="llama3.1:8b"),
+        },
+        "default": False,
+    }
+    KH_EMBEDDINGS["ollama"] = {
+        "spec": {
+            "__type__": "kotaemon.embeddings.OpenAIEmbeddings",
+            "base_url": "http://localhost:11434/v1/",
+            "model": config("LOCAL_MODEL_EMBEDDINGS", default="nomic-embed-text"),
+        },
+        "default": False,
+    }
+
+    KH_EMBEDDINGS["local-bge-en"] = {
+        "spec": {
+            "__type__": "kotaemon.embeddings.FastEmbedEmbeddings",
+            "model_name": "BAAI/bge-base-en-v1.5",
+        },
+        "default": False,
+    }
+
+KH_REASONINGS = [
+    "ktem.reasoning.simple.FullQAPipeline",
+    "ktem.reasoning.simple.FullDecomposeQAPipeline",
+    "ktem.reasoning.react.ReactAgentPipeline",
+    "ktem.reasoning.rewoo.RewooAgentPipeline",
+]
+KH_REASONINGS_USE_MULTIMODAL = False
+KH_VLM_ENDPOINT = "{0}/openai/deployments/{1}/chat/completions?api-version={2}".format(
+    config("AZURE_OPENAI_ENDPOINT", default=""),
+    config("OPENAI_VISION_DEPLOYMENT_NAME", default="gpt-4o"),
+    config("OPENAI_API_VERSION", default=""),
+)
+
+
+SETTINGS_APP: dict[str, dict] = {}
+
+
+SETTINGS_REASONING = {
+    "use": {
+        "name": "Reasoning options",
+        "value": None,
+        "choices": [],
+        "component": "radio",
+    },
+    "lang": {
+        "name": "Language",
+        "value": "en",
+        "choices": [("English", "en"), ("Japanese", "ja"), ("Vietnamese", "vi")],
+        "component": "dropdown",
+    },
+    "max_context_length": {
+        "name": "Max context length (LLM)",
+        "value": 32000,
+        "component": "number",
+    },
+}
+
+
+KH_INDEX_TYPES = [
+    "ktem.index.file.FileIndex",
+    "ktem.index.file.graph.GraphRAGIndex",
+]
+KH_INDICES = [
+    {
+        "name": "File",
+        "config": {
+            "supported_file_types": (
+                ".png, .jpeg, .jpg, .tiff, .tif, .pdf, .xls, .xlsx, .doc, .docx, "
+                ".pptx, .csv, .html, .mhtml, .txt, .zip"
+            ),
+            "private": False,
+        },
+        "index_type": "ktem.index.file.FileIndex",
+    },
+    {
+        "name": "GraphRAG",
+        "config": {
+            "supported_file_types": (
+                ".png, .jpeg, .jpg, .tiff, .tif, .pdf, .xls, .xlsx, .doc, .docx, "
+                ".pptx, .csv, .html, .mhtml, .txt, .zip"
+            ),
+            "private": False,
+        },
+        "index_type": "ktem.index.file.graph.GraphRAGIndex",
+    },
+]

ktem_app_data.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939929c877f3ba49cb82fbf7743e4ab383a3e60d8c4581c521713fa240a96e17
+size 330285315