created v1.0 Docker Image for ChromaDB Server

categorizer/categorizer.go

@@ -1,4 +1,4 @@
-package categorizer
+package main
 
 import (
 	"categorizer/analysis"

chroma-image/Dockerfile

@@ -0,0 +1,15 @@
+FROM python:latest
+WORKDIR /app
+COPY requirements.txt /app/
+#RUN apt-get update && apt-get install -y python3 && apt-get install -y python3-pip
+RUN pip install -r requirements.txt
+RUN mkdir /app/vectorDB
+
+#COPY /files/* /app/vectorDB
+#COPY restoreDb.py /app/
+
+#RUN python3 restoreDb.py
+
+EXPOSE 8000
+
+CMD chroma run # --path /vectorDB

chroma-image/files/dataset_info.json

@@ -0,0 +1,29 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "id": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "embedding": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "metadata": {
+      "file": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "document": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "MIT"
+}

chroma-image/files/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "c6177d3da57accdd",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

chroma-image/requirements.txt

@@ -0,0 +1,3 @@
+chroma-datasets==0.1.5
+chroma-hnswlib==0.7.3
+chromadb==0.4.14

chroma-image/restoreDb.py

@@ -0,0 +1,5 @@
+import chromadb
+from chroma_datasets.utils import import_chroma_exported_hf_dataset_from_disk
+
+cl = chromadb.HttpClient("0.0.0.0", 8000)
+collection = import_chroma_exported_hf_dataset_from_disk(cl, "../iTACA/vectorDB", "payloads")

chroma-image/start_chroma_docker.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+docker run -p 8000:8000 -d chroma-server 
+sleep 5 
+python3 restoreDb.py