[version] bump package version to v0.0.87 (#883)

Co-authored-by: Deven Patel <deven298@yahoo.com>

docs/mint.json

@@ -125,7 +125,7 @@
   "isWhiteLabeled": true,
   "analytics": {
     "posthog": {
-      "apiKey": "phc_MSQ1GVfzkm7dRpktoKUGzWPlpkYhmVpcUtmLk1RwkQs",
+      "apiKey": "phc_PHQDA5KwztijnSojsxJ2c1DuJd52QCzJzT2xnSGvjN2",
       "apiHost": "https://app.embedchain.ai/ingest"
     }
   },

embedchain/data_formatter/data_formatter.py

@@ -1,4 +1,5 @@
 from importlib import import_module
+
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config import AddConfig
 from embedchain.config.add_config import ChunkerConfig, LoaderConfig

embedchain/loaders/json.py

@@ -1,24 +1,56 @@
 import hashlib
+import json
+import os
+import re
 
-from langchain.document_loaders.json_loader import \
-    JSONLoader as LangchainJSONLoader
+import requests
 
 from embedchain.loaders.base_loader import BaseLoader
 
-langchain_json_jq_schema = 'to_entries | map("\(.key): \(.value|tostring)") | .[]'
+VALID_URL_PATTERN = "^https:\/\/[0-9A-z.]+.[0-9A-z.]+.[a-z]+\/.*\.json$"
 
 
 class JSONLoader(BaseLoader):
     @staticmethod
     def load_data(content):
         """Load a json file. Each data point is a key value pair."""
+        try:
+            from llama_hub.jsondata.base import \
+                JSONDataReader as LLHBUBJSONLoader
+        except ImportError:
+            raise Exception(
+                f"Couldn't import the required packages to load {content}, \
+                Do `pip install --upgrade 'embedchain[json]`"
+            )
+
+        loader = LLHBUBJSONLoader()
+
+        if not isinstance(content, str):
+            print(f"Invaid content input. Provide the correct path to the json file saved locally in {content}")
+
         data = []
         data_content = []
-        loader = LangchainJSONLoader(content, text_content=False, jq_schema=langchain_json_jq_schema)
-        docs = loader.load()
+
+        # Load json data from various sources. TODO: add support for dictionary
+        if os.path.isfile(content):
+            with open(content, "r") as json_file:
+                json_data = json.load(json_file)
+        elif re.match(VALID_URL_PATTERN, content):
+            response = requests.get(content)
+            if response.status_code == 200:
+                json_data = response.json()
+            else:
+                raise ValueError(
+                    f"Loading data from the given url: {content} failed. \
+                    Make sure the url is working."
+                )
+        else:
+            raise ValueError(f"Invalid content to load json data from: {content}")
+
+        docs = loader.load_data(json_data)
         for doc in docs:
-            meta_data = doc.metadata
-            data.append({"content": doc.page_content, "meta_data": {"url": content, "row": meta_data["seq_num"]}})
-            data_content.append(doc.page_content)
+            doc_content = doc.text
+            data.append({"content": doc_content, "meta_data": {"url": content}})
+            data_content.append(doc_content)
         doc_id = hashlib.sha256((content + ", ".join(data_content)).encode()).hexdigest()
         return {"doc_id": doc_id, "data": data}

embedchain/telemetry/posthog.py

@@ -17,7 +17,7 @@ logger = logging.getLogger(__name__)
 
 class AnonymousTelemetry:
     def __init__(self, host="https://app.posthog.com", enabled=True):
-        self.project_api_key = "phc_XnMmNHzwxE7PVHX4mD2r8K6nfxVM48a2sq2U3N1p2lO"
+        self.project_api_key = "phc_PHQDA5KwztijnSojsxJ2c1DuJd52QCzJzT2xnSGvjN2"
         self.host = host
         self.posthog = Posthog(project_api_key=self.project_api_key, host=self.host)
         self.user_id = self.get_user_id()

poetry.lock

@@ -2620,6 +2620,31 @@ files = [
     {file = "jq-1.6.0.tar.gz", hash = "sha256:c7711f0c913a826a00990736efa6ffc285f8ef433414516bb14b7df971d6c1ea"},
 ]
 
+[[package]]
+name = "jsonpatch"
+version = "1.33"
+description = "Apply JSON-Patches (RFC 6902)"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
+files = [
+    {file = "jsonpatch-1.33-py2.py3-none-any.whl", hash = "sha256:0ae28c0cd062bbd8b8ecc26d7d164fbbea9652a1a3693f3b956c1eae5145dade"},
+    {file = "jsonpatch-1.33.tar.gz", hash = "sha256:9fcd4009c41e6d12348b4a0ff2563ba56a2923a7dfee731d004e212e1ee5030c"},
+]
+
+[package.dependencies]
+jsonpointer = ">=1.9"
+
+[[package]]
+name = "jsonpointer"
+version = "2.4"
+description = "Identify specific nodes in a JSON document (RFC 6901)"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
+files = [
+    {file = "jsonpointer-2.4-py2.py3-none-any.whl", hash = "sha256:15d51bba20eea3165644553647711d150376234112651b4f1811022aecad7d7a"},
+    {file = "jsonpointer-2.4.tar.gz", hash = "sha256:585cee82b70211fa9e6043b7bb89db6e1aa49524340dde8ad6b63206ea689d88"},
+]
+
 [[package]]
 name = "kiwisolver"
 version = "1.4.5"
@@ -2735,20 +2760,22 @@ files = [
 
 [[package]]
 name = "langchain"
-version = "0.0.279"
+version = "0.0.303"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain-0.0.279-py3-none-any.whl", hash = "sha256:d91e65b3a210e9b52e42ed67c65d76caeaa3195ff097217f5ab2ca477bd3ae27"},
-    {file = "langchain-0.0.279.tar.gz", hash = "sha256:344e33d73c76ae35cdd8c3ba16c965bac29e0e889c93064718c5982002cbe30c"},
+    {file = "langchain-0.0.303-py3-none-any.whl", hash = "sha256:1745961f66b60bc3b513820a34c560dd37c4ba4b7499ba82545dc4816d0133bd"},
+    {file = "langchain-0.0.303.tar.gz", hash = "sha256:84d2727eb8b3b27a9d0aa0da9f05408c2564a4a923c7d5b154a16e488430e725"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
+anyio = "<4.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
-dataclasses-json = ">=0.5.7,<0.6.0"
-langsmith = ">=0.0.21,<0.1.0"
+dataclasses-json = ">=0.5.7,<0.7"
+jsonpatch = ">=1.33,<2.0"
+langsmith = ">=0.0.38,<0.1.0"
 numexpr = ">=2.8.4,<3.0.0"
 numpy = ">=1,<2"
 pydantic = ">=1,<3"
@@ -2764,7 +2791,7 @@ clarifai = ["clarifai (>=9.1.0)"]
 cohere = ["cohere (>=4,<5)"]
 docarray = ["docarray[hnswlib] (>=0.32.0,<0.33.0)"]
 embeddings = ["sentence-transformers (>=2,<3)"]
-extended-testing = ["amazon-textract-caller (<2)", "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 (>=0.0.7,<0.0.8)", "chardet (>=5.1.0,<6.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "openai (>=0,<1)", "openapi-schema-pydantic (>=1.2,<2.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "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)", "requests-toolbelt (>=1.0.0,<2.0.0)", "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)", "tqdm (>=4.48.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
+extended-testing = ["amazon-textract-caller (<2)", "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)", "dashvector (>=1.0.1,<2.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "openai (>=0,<1)", "openapi-schema-pydantic (>=1.2,<2.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "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)", "requests-toolbelt (>=1.0.0,<2.0.0)", "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)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
 javascript = ["esprima (>=4.0.1,<5.0.0)"]
 llms = ["clarifai (>=9.1.0)", "cohere (>=4,<5)", "huggingface_hub (>=0,<1)", "manifest-ml (>=0.0.1,<0.0.2)", "nlpcloud (>=1,<2)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
 openai = ["openai (>=0,<1)", "tiktoken (>=0.3.2,<0.4.0)"]
@@ -7196,4 +7223,4 @@ whatsapp = ["flask", "twilio"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.13"
-content-hash = "fad388baca92d2669530c2d928920e9f7abbe0ad74786b34dc915603b4a08a17"
+content-hash = "17a067a3994a2f17c55e6ee48a3f8ec664a94112951183070ed34d40d25a7533"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.0.85"
+version = "0.0.87"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",
@@ -90,7 +90,7 @@ color = true
 [tool.poetry.dependencies]
 python = ">=3.9,<3.13"
 python-dotenv = "^1.0.0"
-langchain = "^0.0.279"
+langchain = "^0.0.303"
 requests = "^2.31.0"
 openai = ">=0.28.0"
 chromadb = "^0.4.8"

tests/loaders/test_json.py

@@ -1,32 +1,91 @@
 import hashlib
-from unittest.mock import patch
 
-from langchain.docstore.document import Document
-from langchain.document_loaders.json_loader import \
-    JSONLoader as LangchainJSONLoader
+import pytest
+from llama_index.readers.schema.base import Document
 
 from embedchain.loaders.json import JSONLoader
 
 
-def test_load_data():
-    mock_document = [
-        Document(page_content="content1", metadata={"seq_num": 1}),
-        Document(page_content="content2", metadata={"seq_num": 2}),
+def test_load_data(mocker):
+    content = "temp.json"
+
+    mock_document = {
+        "doc_id": hashlib.sha256((content + ", ".join(["content1", "content2"])).encode()).hexdigest(),
+        "data": [
+            {"content": "content1", "meta_data": {"url": content}},
+            {"content": "content2", "meta_data": {"url": content}},
+        ],
+    }
+
+    mocker.patch("embedchain.loaders.json.JSONLoader.load_data", return_value=mock_document)
+
+    json_loader = JSONLoader()
+
+    result = json_loader.load_data(content)
+
+    assert "doc_id" in result
+    assert "data" in result
+
+    expected_data = [
+        {"content": "content1", "meta_data": {"url": content}},
+        {"content": "content2", "meta_data": {"url": content}},
     ]
-    with patch.object(LangchainJSONLoader, "load", return_value=mock_document):
-        content = "temp.json"
 
-        result = JSONLoader.load_data(content)
+    assert result["data"] == expected_data
 
-        assert "doc_id" in result
-        assert "data" in result
+    expected_doc_id = hashlib.sha256((content + ", ".join(["content1", "content2"])).encode()).hexdigest()
+    assert result["doc_id"] == expected_doc_id
 
-        expected_data = [
-            {"content": "content1", "meta_data": {"url": content, "row": 1}},
-            {"content": "content2", "meta_data": {"url": content, "row": 2}},
-        ]
 
-        assert result["data"] == expected_data
+def test_load_data_url(mocker):
+    content = "https://example.com/posts.json"
 
-        expected_doc_id = hashlib.sha256((content + ", ".join(["content1", "content2"])).encode()).hexdigest()
-        assert result["doc_id"] == expected_doc_id
+    mocker.patch("os.path.isfile", return_value=False)  # Mocking os.path.isfile to simulate a URL case
+    mocker.patch(
+        "llama_hub.jsondata.base.JSONDataReader.load_data",
+        return_value=[Document(text="content1"), Document(text="content2")],
+    )
+
+    mock_response = mocker.Mock()
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"document1": "content1", "document2": "content2"}
+
+    mocker.patch("requests.get", return_value=mock_response)
+
+    result = JSONLoader.load_data(content)
+
+    assert "doc_id" in result
+    assert "data" in result
+
+    expected_data = [
+        {"content": "content1", "meta_data": {"url": content}},
+        {"content": "content2", "meta_data": {"url": content}},
+    ]
+
+    assert result["data"] == expected_data
+
+    expected_doc_id = hashlib.sha256((content + ", ".join(["content1", "content2"])).encode()).hexdigest()
+    assert result["doc_id"] == expected_doc_id
+
+
+def test_load_data_invalid_content(mocker):
+    mocker.patch("os.path.isfile", return_value=False)
+    mocker.patch("requests.get")
+
+    content = "123"
+
+    with pytest.raises(ValueError, match="Invalid content to load json data from"):
+        JSONLoader.load_data(content)
+
+
+def test_load_data_invalid_url(mocker):
+    mocker.patch("os.path.isfile", return_value=False)
+
+    mock_response = mocker.Mock()
+    mock_response.status_code = 404
+    mocker.patch("requests.get", return_value=mock_response)
+
+    content = "http://invalid-url.com/"
+
+    with pytest.raises(ValueError, match=f"Invalid content to load json data from: {content}"):
+        JSONLoader.load_data(content)

tests/telemetry/test_posthog.py

@@ -1,5 +1,6 @@
-import os
 import logging
+import os
+
 from embedchain.telemetry.posthog import AnonymousTelemetry