Enhancement: Blockchain Document Loader with better Metadata support (#3710)

This PR includes some minor alignment updates, including:

- metadata object extended to support contractAddress, blockchainType,
and tokenId
- notebook doc better aligned to standard langchain format
- startToken changed from int to str to support multiple hex value types
on the Alchemy API

The updated metadata will look like the below. It's possible for a
single contractAddress to exist across multiple blockchains (e.g.
Ethereum, Polygon, etc.) so it's important to include the
blockchainType.

```
 metadata = {"source": self.contract_address, 
                      "blockchain": self.blockchainType,
                      "tokenId": tokenId}
```

docs/modules/indexes/document_loaders/examples/blockchain.ipynb

@@ -7,7 +7,7 @@
         "id": "vm8vn9t8DvC_"
       },
       "source": [
-        "# Blockchain Document Loader"
+        "# Blockchain"
       ]
     },
     {
@@ -31,7 +31,7 @@
         "\n",
         "Initially this Loader supports:\n",
         "\n",
-        "\n",
+        "*   Loading NFTs as Documents from NFT Smart Contracts (ERC721 and ERC1155)\n",
         "*   Ethereum Maninnet, Ethereum Testnet, Polgyon Mainnet, Polygon Testnet (default is eth-mainnet)\n",
         "*   Alchemy's getNFTsForCollection API\n",
         "\n",
@@ -39,14 +39,14 @@
         "\n",
         "*   Additional APIs can be added (e.g. Tranction-related APIs)\n",
         "\n",
-        "To run this notebook, the user will need:\n",
+        "This Document Loader Requires:\n",
-        "\n",
         "\n",
-        "*   An OpenAI key (for OpenAI models)\n",
         "*   A free [Alchemy API Key](https://www.alchemy.com/)\n",
         "\n",
+        "The output takes the following format:\n",
         "\n",
-        "\n"
+        "- pageContent= Individual NFT\n",
+        "- metadata={'source': '0x1a92f7381b9f03921564a437210bb9396471050c', 'blockchain': 'eth-mainnet', 'tokenId': '0x15'})"
       ]
     },
     {
@@ -54,55 +54,16 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup"
+        "## Load NFTs into Document Loader"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 48,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Note: you may need to restart the kernel to use updated packages.\n"
-          ]
-        }
-      ],
-      "source": [
-        "%pip install langchain -q"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 49,
+      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langchain.document_loaders import BlockchainDocumentLoader\n",
-        "from langchain.document_loaders.blockchain import BlockchainType\n",
-        "import os"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 50,
       "metadata": {},
       "outputs": [],
       "source": [
-        "alchemyApiKey = \"get your own key from https://www.alchemy.com/\" \n",
+        "alchemyApiKey = \"get from https://www.alchemy.com/ and set in environment variable ALCHEMY_API_KEY\""
-        "os.environ[\"ALCHEMY_API_KEY\"] = alchemyApiKey"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "nzuPWRaBNCMx"
-      },
-      "source": [
-        "## Create a Blockchain Document Loader"
       ]
     },
     {
@@ -115,29 +76,18 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 24,
+      "execution_count": null,
       "metadata": {
         "id": "J3LWHARC-Kn0"
       },
-      "outputs": [
+      "outputs": [],
-        {
-          "data": {
-            "text/plain": [
-              "[Document(page_content=\"{'contract': {'address': '0xbc4ca0eda7647a8ab7c2061c2e118a18a936f13d'}, 'id': {'tokenId': '0x0000000000000000000000000000000000000000000000000000000000000000', 'tokenMetadata': {'tokenType': 'ERC721'}}, 'title': '', 'description': '', 'tokenUri': {'gateway': 'https://alchemy.mypinata.cloud/ipfs/QmeSjSinHpPnmXmspMjwiXyN6zS4E9zccariGR3jxcaWtq/0', 'raw': 'ipfs://QmeSjSinHpPnmXmspMjwiXyN6zS4E9zccariGR3jxcaWtq/0'}, 'media': [{'gateway': 'https://nft-cdn.alchemy.com/eth-mainnet/415d618f5fef7bfe683e02d4653c4289', 'thumbnail': 'https://res.cloudinary.com/alchemyapi/image/upload/thumbnailv2/eth-mainnet/415d618f5fef7bfe683e02d4653c4289', 'raw': 'ipfs://QmRRPWG96cmgTn2qSzjwr2qvfNEuhunv6FNeMFGa9bx6mQ', 'format': 'png', 'bytes': 133270}], 'metadata': {'image': 'ipfs://QmRRPWG96cmgTn2qSzjwr2qvfNEuhunv6FNeMFGa9bx6mQ', 'attributes': [{'value': 'Silver Hoop', 'trait_type': 'Earring'}, {'value': 'Orange', 'trait_type': 'Background'}, {'value': 'Robot', 'trait_type': 'Fur'}, {'value': 'Striped Tee', 'trait_type': 'Clothes'}, {'value': 'Discomfort', 'trait_type': 'Mouth'}, {'value': 'X Eyes', 'trait_type': 'Eyes'}]}, 'timeLastUpdated': '2023-04-18T04:05:27.817Z', 'contractMetadata': {'name': 'BoredApeYachtClub', 'symbol': 'BAYC', 'totalSupply': '10000', 'tokenType': 'ERC721', 'contractDeployer': '0xaba7161a7fb69c88e16ed9f455ce62b791ee4d03', 'deployedBlockNumber': 12287507, 'openSea': {'floorPrice': 68.16, 'collectionName': 'Bored Ape Yacht Club', 'safelistRequestStatus': 'verified', 'imageUrl': 'https://i.seadn.io/gae/Ju9CkWtV-1Okvf45wo8UctR-M9He2PjILP0oOvxE89AyiPPGtrR3gysu1Zgy0hjd2xKIgjJJtWIc0ybj4Vd7wv8t3pxDGHoJBzDB?w=500&auto=format', 'description': 'The Bored Ape Yacht Club is a collection of 10,000 unique Bored Ape NFTs— unique digital collectibles living on the Ethereum blockchain. Your Bored Ape doubles as your Yacht Club membership card, and grants access to members-only benefits, the first of which is access to THE BATHROOM, a collaborative graffiti board. Future areas and perks can be unlocked by the community through roadmap activation. Visit www.BoredApeYachtClub.com for more details.', 'externalUrl': 'http://www.boredapeyachtclub.com/', 'twitterUsername': 'BoredApeYC', 'discordUrl': 'https://discord.gg/3P5K3dzgdB', 'lastIngestedAt': '2023-03-21T03:54:33.000Z'}}}\", metadata={'tokenId': '0x0000000000000000000000000000000000000000000000000000000000000000'}),\n",
-              " Document(page_content=\"{'contract': {'address': '0xbc4ca0eda7647a8ab7c2061c2e118a18a936f13d'}, 'id': {'tokenId': '0x0000000000000000000000000000000000000000000000000000000000000001', 'tokenMetadata': {'tokenType': 'ERC721'}}, 'title': '', 'description': '', 'tokenUri': {'gateway': 'https://alchemy.mypinata.cloud/ipfs/QmeSjSinHpPnmXmspMjwiXyN6zS4E9zccariGR3jxcaWtq/1', 'raw': 'ipfs://QmeSjSinHpPnmXmspMjwiXyN6zS4E9zccariGR3jxcaWtq/1'}, 'media': [{'gateway': 'https://nft-cdn.alchemy.com/eth-mainnet/65558a4d0c5b0c56fbc50bf03f55e3fa', 'thumbnail': 'https://res.cloudinary.com/alchemyapi/image/upload/thumbnailv2/eth-mainnet/65558a4d0c5b0c56fbc50bf03f55e3fa', 'raw': 'ipfs://QmPbxeGcXhYQQNgsC6a36dDyYUcHgMLnGKnF8pVFmGsvqi', 'format': 'png', 'bytes': 171425}], 'metadata': {'image': 'ipfs://QmPbxeGcXhYQQNgsC6a36dDyYUcHgMLnGKnF8pVFmGsvqi', 'attributes': [{'value': 'Grin', 'trait_type': 'Mouth'}, {'value': 'Vietnam Jacket', 'trait_type': 'Clothes'}, {'value': 'Orange', 'trait_type': 'Background'}, {'value': 'Blue Beams', 'trait_type': 'Eyes'}, {'value': 'Robot', 'trait_type': 'Fur'}]}, 'timeLastUpdated': '2023-04-24T04:37:37.738Z', 'contractMetadata': {'name': 'BoredApeYachtClub', 'symbol': 'BAYC', 'totalSupply': '10000', 'tokenType': 'ERC721', 'contractDeployer': '0xaba7161a7fb69c88e16ed9f455ce62b791ee4d03', 'deployedBlockNumber': 12287507, 'openSea': {'floorPrice': 68.16, 'collectionName': 'Bored Ape Yacht Club', 'safelistRequestStatus': 'verified', 'imageUrl': 'https://i.seadn.io/gae/Ju9CkWtV-1Okvf45wo8UctR-M9He2PjILP0oOvxE89AyiPPGtrR3gysu1Zgy0hjd2xKIgjJJtWIc0ybj4Vd7wv8t3pxDGHoJBzDB?w=500&auto=format', 'description': 'The Bored Ape Yacht Club is a collection of 10,000 unique Bored Ape NFTs— unique digital collectibles living on the Ethereum blockchain. Your Bored Ape doubles as your Yacht Club membership card, and grants access to members-only benefits, the first of which is access to THE BATHROOM, a collaborative graffiti board. Future areas and perks can be unlocked by the community through roadmap activation. Visit www.BoredApeYachtClub.com for more details.', 'externalUrl': 'http://www.boredapeyachtclub.com/', 'twitterUsername': 'BoredApeYC', 'discordUrl': 'https://discord.gg/3P5K3dzgdB', 'lastIngestedAt': '2023-03-21T03:54:33.000Z'}}}\", metadata={'tokenId': '0x0000000000000000000000000000000000000000000000000000000000000001'})]"
-            ]
-          },
-          "execution_count": 24,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
       "source": [
         "contractAddress = \"0xbc4ca0eda7647a8ab7c2061c2e118a18a936f13d\" # Bored Ape Yacht Club contract address\n",
         "\n",
         "blockchainType = BlockchainType.ETH_MAINNET  #default value, optional parameter\n",
         "\n",
-        "blockchainLoader = BlockchainDocumentLoader(contractAddress)\n",
+        "blockchainLoader = BlockchainDocumentLoader(contract_address=contractAddress,\n",
+        "                                            api_key=alchemyApiKey)\n",
         "\n",
         "nfts = blockchainLoader.load()\n",
         "\n",
@@ -154,265 +104,22 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 36,
+      "execution_count": null,
       "metadata": {},
-      "outputs": [
+      "outputs": [],
-        {
-          "data": {
-            "text/plain": [
-              "[Document(page_content=\"{'contract': {'address': '0x448676ffcd0adf2d85c1f0565e8dde6924a9a7d9'}, 'id': {'tokenId': '0x01', 'tokenMetadata': {'tokenType': 'ERC1155'}}, 'title': 'Wyatt Horton #0001', 'description': 'A sleepy capybara', 'tokenUri': {'gateway': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/metadata/1.json', 'raw': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/metadata/1.json'}, 'media': [{'gateway': 'https://nft-cdn.alchemy.com/matic-mainnet/9085e06ff9f6c9074de91801d1c72d26', 'thumbnail': 'https://res.cloudinary.com/alchemyapi/image/upload/thumbnailv2/matic-mainnet/9085e06ff9f6c9074de91801d1c72d26', 'raw': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/images/1.png', 'format': 'png', 'bytes': 769622}], 'metadata': {'name': 'Wyatt Horton #0001', 'description': 'A sleepy capybara', 'image': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/images/1.png', 'attributes': [{'value': 'Avatar', 'trait_type': 'Type'}, {'value': 'Animal', 'trait_type': 'Category'}, {'value': 'Capybara', 'trait_type': 'Class'}, {'value': 'Fall 2022', 'trait_type': 'Collection'}, {'value': 'Furry', 'trait_type': 'Feature'}]}, 'timeLastUpdated': '2023-04-20T14:38:24.947Z', 'contractMetadata': {'name': 'Smoothstack - Avatars', 'symbol': 'SMTH', 'tokenType': 'ERC1155', 'contractDeployer': '0x23075b2523c6563b06920a302a8be4f90ef6e974', 'deployedBlockNumber': 34752389, 'openSea': {'lastIngestedAt': '2023-04-17T20:59:42.000Z'}}}\", metadata={'tokenId': '0x01'}),\n",
-              " Document(page_content=\"{'contract': {'address': '0x448676ffcd0adf2d85c1f0565e8dde6924a9a7d9'}, 'id': {'tokenId': '0x02', 'tokenMetadata': {'tokenType': 'ERC1155'}}, 'title': 'Dylan Leisler #0002', 'description': 'A chipper cat with a big, red bowtie', 'tokenUri': {'gateway': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/metadata/2.json', 'raw': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/metadata/2.json'}, 'media': [{'gateway': 'https://nft-cdn.alchemy.com/matic-mainnet/67c3c7ccef44b32bf2ce758e8e73dbcd', 'thumbnail': 'https://res.cloudinary.com/alchemyapi/image/upload/thumbnailv2/matic-mainnet/67c3c7ccef44b32bf2ce758e8e73dbcd', 'raw': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/images/2.png', 'format': 'png', 'bytes': 1187749}], 'metadata': {'name': 'Dylan Leisler #0002', 'description': 'A chipper cat with a big, red bowtie', 'image': 'https://storage.googleapis.com/minted-nfts/smoothstack/avatars/images/2.png', 'attributes': [{'value': 'Avatar', 'trait_type': 'Type'}, {'value': 'Animal', 'trait_type': 'Category'}, {'value': 'Cat', 'trait_type': 'Class'}, {'value': 'Fall 2022', 'trait_type': 'Collection'}, {'value': 'Red Bowtie', 'trait_type': 'Feature'}]}, 'timeLastUpdated': '2023-04-23T13:38:29.316Z', 'contractMetadata': {'name': 'Smoothstack - Avatars', 'symbol': 'SMTH', 'tokenType': 'ERC1155', 'contractDeployer': '0x23075b2523c6563b06920a302a8be4f90ef6e974', 'deployedBlockNumber': 34752389, 'openSea': {'lastIngestedAt': '2023-04-17T20:59:42.000Z'}}}\", metadata={'tokenId': '0x02'})]"
-            ]
-          },
-          "execution_count": 36,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
       "source": [
         "contractAddress = \"0x448676ffCd0aDf2D85C1f0565e8dde6924A9A7D9\" # Polygon Mainnet contract address\n",
         "\n",
         "blockchainType = BlockchainType.POLYGON_MAINNET \n",
         "\n",
-        "blockchainLoader = BlockchainDocumentLoader(contractAddress, blockchainType)\n",
+        "blockchainLoader = BlockchainDocumentLoader(contract_address=contractAddress, \n",
+        "                                            blockchainType=blockchainType, \n",
+        "                                            api_key=alchemyApiKey)\n",
         "\n",
         "nfts = blockchainLoader.load()\n",
         "\n",
         "nfts[:2]"
       ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## (Optional) Using the Blockchain Document Loader"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "_PGkFfMCB8J3"
-      },
-      "source": [
-        "### Setup Splitter and Index"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 37,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Note: you may need to restart the kernel to use updated packages.\n"
-          ]
-        }
-      ],
-      "source": [
-        "%pip install sentence_transformers chromadb openai tiktoken -q"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 38,
-      "metadata": {
-        "id": "BwxxopOCCABh"
-      },
-      "outputs": [],
-      "source": [
-        "from langchain.indexes import VectorstoreIndexCreator\n",
-        "from langchain.embeddings import HuggingFaceEmbeddings\n",
-        "from langchain.text_splitter import RecursiveCharacterTextSplitter"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 39,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "JE_myAulCDSZ",
-        "outputId": "99e16b6a-03b4-4e67-d4b4-9dd611a866ef"
-      },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "NUMBER OF DOCUMENTS:  424\n"
-          ]
-        }
-      ],
-      "source": [
-        "text_splitter = RecursiveCharacterTextSplitter(chunk_size=400, chunk_overlap=0)\n",
-        "\n",
-        "docs = text_splitter.split_documents(nfts)\n",
-        "print(\"NUMBER OF DOCUMENTS: \", len(docs))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 40,
-      "metadata": {
-        "id": "d83yFuAuCKQS"
-      },
-      "outputs": [
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "Using embedded DuckDB without persistence: data will be transient\n"
-          ]
-        }
-      ],
-      "source": [
-        "index = VectorstoreIndexCreator(\n",
-        "    embedding=HuggingFaceEmbeddings(),\n",
-        "    text_splitter=text_splitter).from_loaders([blockchainLoader])"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "y0VfObeXDEXB"
-      },
-      "source": [
-        "## Setup Models and Chains"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 42,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "openAiKey = \"put OpenAI key here\"\n",
-        "os.environ[\"OPENAI_API_KEY\"] = openAiKey"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 31,
-      "metadata": {
-        "id": "hiNjDzP9C4pA"
-      },
-      "outputs": [],
-      "source": [
-        "from langchain.chains import RetrievalQA\n",
-        "from langchain.llms import OpenAI"
-      ]
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "u-xDlKPaC_xg"
-      },
-      "source": [
-        "### Retrieval Chain"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 43,
-      "metadata": {
-        "id": "BqP00JovC9R4"
-      },
-      "outputs": [],
-      "source": [
-        "llmOpenAI = OpenAI()\n",
-        "\n",
-        "chainQA = RetrievalQA.from_chain_type(llm=llmOpenAI, \n",
-        "                                    chain_type=\"map_reduce\",\n",
-        "                                    retriever=index.vectorstore.as_retriever(), \n",
-        "                                    verbose=True,\n",
-        "                                    input_key=\"question\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 44,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 122
-        },
-        "id": "2Y3cVVKZDVNq",
-        "outputId": "dfeea416-5193-47cf-e9dc-c17a5c1cd780"
-      },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "' Popular attributes include \"Avatar\" (Type), \"Character\" (Category), and \"Human\" or \"Wizard\" (Class).'"
-            ]
-          },
-          "execution_count": 44,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "chainQA.run(\"What are some of the popular attributes?\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 122
-        },
-        "id": "7o6ArPo9DXbz",
-        "outputId": "b1f8ad43-27c7-4cdb-95a7-8c8bd6381c5a"
-      },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "application/vnd.google.colaboratory.intrinsic+json": {
-              "type": "string"
-            },
-            "text/plain": [
-              "' There are 10,000 unique Bored Ape NFTs.'"
-            ]
-          },
-          "execution_count": 32,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "chainQA.run(\"How many NFTs are there?\")"
-      ]
     }
   ],
   "metadata": {

langchain/document_loaders/blockchain.py

@@ -26,10 +26,14 @@ class BlockchainDocumentLoader(BaseLoader):
 
     The Loader uses the Alchemy API to interact with the blockchain.
 
+    The API returns 100 NFTs per request and can be paginated using the
+    startToken parameter.
+
     ALCHEMY_API_KEY environment variable must be set to use this loader.
 
     Future versions of this loader can:
         - Support additional Alchemy APIs (e.g. getTransactions, etc.)
+        - Support additional blockain APIs (e.g. Infura, Opensea, etc.)
     """
 
     def __init__(
@@ -37,7 +41,7 @@ class BlockchainDocumentLoader(BaseLoader):
         contract_address: str,
         blockchainType: BlockchainType = BlockchainType.ETH_MAINNET,
         api_key: str = "docs-demo",
-        startToken: int = 0,
+        startToken: str = "",
     ):
         self.contract_address = contract_address
         self.blockchainType = blockchainType.value
@@ -75,6 +79,10 @@ class BlockchainDocumentLoader(BaseLoader):
         for item in items:
             content = str(item)
             tokenId = item["id"]["tokenId"]
-            metadata = {"tokenId": tokenId}
+            metadata = {
+                "source": self.contract_address,
+                "blockchain": self.blockchainType,
+                "tokenId": tokenId,
+            }
             result.append(Document(page_content=content, metadata=metadata))
         return result

tests/integration_tests/document_loaders/test_blockchain.py

@@ -26,7 +26,7 @@ def test_get_nfts_with_pagination() -> None:
     contract_address = (
         "0x1a92f7381b9f03921564a437210bb9396471050c"  # CoolCats contract address
     )
-    startToken = 20
+    startToken = "20"
 
     result = BlockchainDocumentLoader(
         contract_address,