run-llama · jerryjliu · Aug 21, 2023 · Jul 27, 2023 · Jul 31, 2023 · Aug 1, 2023
diff --git a/llama_hub/airbyte_cdk/.gitignore b/llama_hub/airbyte_cdk/.gitignore
@@ -0,0 +1 @@
+test.py
diff --git a/llama_hub/airbyte_cdk/README.md b/llama_hub/airbyte_cdk/README.md
@@ -0,0 +1,48 @@
+# Airbyte CDK Loader
+
+The Airbyte CDK Loader is a shim for sources created using the [Airbyte Python CDK](https://docs.airbyte.com/connector-development/cdk-python/). It allows you to load data from any Airbyte source into LlamaIndex.
+
+## Installation
+
+* Install llama_hub: `pip install llama_hub`
+* Install airbyte-cdk: `pip install airbyte-cdk`
+* Install a source via git (or implement your own): `pip install git+https://github.com/airbytehq/airbyte.git@master#egg=source_github&subdirectory=airbyte-integrations/connectors/source-github`
+
+## Usage
+
+Implement and import your own source. You can find lots of resources for how to achieve this on the [Airbyte documentation page](https://docs.airbyte.com/connector-development/).
+
+Here's an example usage of the AirbyteCdkReader.
+
+```python
+from llama_index import download_loader
+from llama_hub.airbyte_cdk.base import AirbyteCDKReader
+from source_github.source import SourceGithub # this is just an example, you can use any source here - this one is loaded from the Airbyte Github repo via pip install git+https://github.com/airbytehq/airbyte.git@master#egg=source_github&subdirectory=airbyte-integrations/connectors/source-github`
+
+
+github_config = {
+    # ...
+}
+reader = AirbyteCDKReader(source_class=SourceGithub,config=github_config)
+documents = reader.load_data(stream_name="issues")
+```
+
+By default all fields are stored as metadata in the documents and the text is set to an empty string. Construct the text of the document by transforming the documents returned by the reader:
+```python
+for doc in documents:
+  doc.text = doc.extra_info["title"]
+```
+
+## Incremental loads
+
+If a stream supports it, this loader can be used to load data incrementally (only returning documents that weren't loaded last time or got updated in the meantime):
+```python
+
+reader = AirbyteCDKReader(source_class=SourceGithub,config=github_config)
+documents = reader.load_data(stream_name="issues")
+current_state = reader.last_state # can be pickled away or stored otherwise
+
+updated_documents = reader.load_data(stream_name="issues", state=current_state) # only loads documents that were updated since last time
+```
+
+This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/jerryjliu/gpt_index/tree/main/gpt_index) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent. See [here](https://github.com/emptycrown/llama-hub/tree/main) for examples.
diff --git a/llama_hub/airbyte_cdk/__init__.py b/llama_hub/airbyte_cdk/__init__.py
diff --git a/llama_hub/airbyte_cdk/base.py b/llama_hub/airbyte_cdk/base.py
@@ -0,0 +1,33 @@
+from typing import Any, List, Mapping, Optional
+
+from llama_index.readers.base import BaseReader
+from llama_index.readers.schema.base import Document
+from airbyte_protocol.models.airbyte_protocol import AirbyteRecordMessage
+from airbyte_cdk.sources.embedded.base_integration import BaseEmbeddedIntegration
+from airbyte_cdk.sources.embedded.runner import CDKRunner
+
+
+class AirbyteCDKReader(BaseReader, BaseEmbeddedIntegration):
+    """AirbyteCDKReader reader.
+
+    Retrieve documents from an Airbyte source implemented using the CDK.
+
+    Args:
+        source_class: The Airbyte source class.
+        config: The config object for the Airbyte source.
+    """
+
+    def __init__(
+        self,
+        source_class: Any,
+        config: Mapping[str, Any],
+    ) -> None:
+        """Initialize with parameters."""
+
+        super().__init__(config=config, runner=CDKRunner(source=source_class(), name=source_class.__name__))
+
+    def _handle_record(self, record: AirbyteRecordMessage, id: Optional[str]) -> Document:
+        return Document(doc_id=id,text="", extra_info=record.data)
+
+    def load_data(self, *args: Any, **load_kwargs: Any) -> List[Document]:
+        return list(self._load_data(*args, **load_kwargs))
diff --git a/llama_hub/airbyte_cdk/requirements.txt b/llama_hub/airbyte_cdk/requirements.txt
@@ -0,0 +1,2 @@
+airbyte-cdk
+airbyte-protocol-models
diff --git a/llama_hub/airbyte_gong/README.md b/llama_hub/airbyte_gong/README.md
@@ -0,0 +1,56 @@
+# Airbyte Gong Loader
+
+The Airbyte Gong Loader allows you to access different Gong objects.
+
+## Installation
+
+* Install llama_hub: `pip install llama_hub`
+* Install the gong source: `pip install airbyte-source-gong`
+
+## Usage
+
+Here's an example usage of the AirbyteGongReader.
+
+```python
+from llama_hub.airbyte_gong.base import AirbyteGongReader
+
+gong_config = {
+    # ...
+}
+reader = AirbyteGongReader(config=gong_config)
+documents = reader.load_data(stream_name="calls")
+```
+
+## Configuration
+
+Check out the [Airbyte documentation page](https://docs.airbyte.com/integrations/sources/gong/) for details about how to configure the reader.
+The JSON schema the config object should adhere to can be found on Github: [https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-gong/source_gong/spec.yaml](https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-gong/source_gong/spec.yaml).
+
+The general shape looks like this:
+```python
+{
+  "access_key": "<access key name>",
+  "access_key_secret": "<access key secret>",
+  "start_date": "<date from which to start retrieving records from in ISO format, e.g. 2020-10-20T00:00:00Z>",
+}
+```
+
+By default all fields are stored as metadata in the documents and the text is set to an empty string. Construct the text of the document by transforming the documents returned by the reader:
+```python
+for doc in documents:
+  doc.text = doc.extra_info["title"]
+```
+
+## Incremental loads
+
+This loader supports loading data incrementally (only returning documents that weren't loaded last time or got updated in the meantime):
+```python
+
+reader = AirbyteGongReader(...so many things...)
+documents = reader.load_data(stream_name="calls")
+current_state = reader.last_state # can be pickled away or stored otherwise
+
+updated_documents = reader.load_data(stream_name="calls", state=current_state) # only loads documents that were updated since last time
+```
+
+This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/jerryjliu/gpt_index/tree/main/gpt_index) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent. See [here](https://github.com/emptycrown/llama-hub/tree/main) for examples.
diff --git a/llama_hub/airbyte_gong/__init__.py b/llama_hub/airbyte_gong/__init__.py
diff --git a/llama_hub/airbyte_gong/base.py b/llama_hub/airbyte_gong/base.py
@@ -0,0 +1,21 @@
+from typing import Any, Mapping
+from llama_hub.airbyte_cdk.base import AirbyteCDKReader
+
+
+class AirbyteGongReader(AirbyteCDKReader):
+    """AirbyteGongReader reader.
+
+    Retrieve documents from Gong 
+
+    Args:
+        config: The config object for the gong source.
+    """
+
+    def __init__(
+        self,
+        config: Mapping[str, Any],
+    ) -> None:
+        """Initialize with parameters."""
+        import source_gong
+
+        super().__init__(source_class=source_gong.SourceGong, config=config)
diff --git a/llama_hub/airbyte_gong/requirements.txt b/llama_hub/airbyte_gong/requirements.txt
@@ -0,0 +1 @@
+airbyte-source-gong
diff --git a/llama_hub/airbyte_hubspot/README.md b/llama_hub/airbyte_hubspot/README.md
@@ -0,0 +1,58 @@
+# Airbyte Hubspot Loader
+
+The Airbyte Hubspot Loader allows you to access different Hubspot objects.
+
+## Installation
+
+* Install llama_hub: `pip install llama_hub`
+* Install the hubspot source: `pip install airbyte-source-hubspot`
+
+## Usage
+
+Here's an example usage of the AirbyteHubspotReader.
+
+```python
+from llama_hub.airbyte_hubspot.base import AirbyteHubspotReader
+
+hubspot_config = {
+    # ...
+}
+reader = AirbyteHubspotReader(config=hubspot_config)
+documents = reader.load_data(stream_name="products")
+```
+
+## Configuration
+
+Check out the [Airbyte documentation page](https://docs.airbyte.com/integrations/sources/hubspot/) for details about how to configure the reader.
+The JSON schema the config object should adhere to can be found on Github: [https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-hubspot/source_hubspot/spec.yaml](https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-hubspot/source_hubspot/spec.yaml).
+
+The general shape looks like this:
+```python
+{
+  "start_date": "<date from which to start retrieving records from in ISO format, e.g. 2020-10-20T00:00:00Z>",
+  "credentials": {
+    "credentials_title": "Private App Credentials",
+    "access_token": "<access token of your private app>"
+  }
+}
+```
+
+By default all fields are stored as metadata in the documents and the text is set to an empty string. Construct the text of the document by transforming the documents returned by the reader:
+```python
+for doc in documents:
+  doc.text = doc.extra_info["title"]
+```
+
+## Incremental loads
+
+This loader supports loading data incrementally (only returning documents that weren't loaded last time or got updated in the meantime):
+```python
+
+reader = AirbyteHubspotReader(...so many things...)
+documents = reader.load_data(stream_name="products")
+current_state = reader.last_state # can be pickled away or stored otherwise
+
+updated_documents = reader.load_data(stream_name="products", state=current_state) # only loads documents that were updated since last time
+```
+
+This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/jerryjliu/gpt_index/tree/main/gpt_index) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent. See [here](https://github.com/emptycrown/llama-hub/tree/main) for examples.
diff --git a/llama_hub/airbyte_hubspot/__init__.py b/llama_hub/airbyte_hubspot/__init__.py
diff --git a/llama_hub/airbyte_hubspot/base.py b/llama_hub/airbyte_hubspot/base.py
@@ -0,0 +1,21 @@
+from typing import Any, Mapping
+from llama_hub.airbyte_cdk.base import AirbyteCDKReader
+
+
+class AirbyteHubspotReader(AirbyteCDKReader):
+    """AirbyteHubspotReader reader.
+
+    Retrieve documents from Hubspot
+
+    Args:
+        config: The config object for the hubspot source.
+    """
+
+    def __init__(
+        self,
+        config: Mapping[str, Any],
+    ) -> None:
+        """Initialize with parameters."""
+        import source_hubspot
+
+        super().__init__(source_class=source_hubspot.SourceHubspot, config=config)
diff --git a/llama_hub/airbyte_hubspot/requirements.txt b/llama_hub/airbyte_hubspot/requirements.txt
@@ -0,0 +1 @@
+source_hubspot
diff --git a/llama_hub/airbyte_salesforce/README.md b/llama_hub/airbyte_salesforce/README.md
@@ -0,0 +1,63 @@
+# Airbyte Salesforce Loader
+
+The Airbyte Salesforce Loader allows you to access different Salesforce objects.
+
+## Installation
+
+* Install llama_hub: `pip install llama_hub`
+* Install the salesforce source: `pip install airbyte-source-salesforce`
+
+## Usage
+
+Here's an example usage of the AirbyteSalesforceReader.
+
+```python
+from llama_hub.airbyte_salesforce.base import AirbyteSalesforceReader
+
+salesforce_config = {
+    # ...
+}
+reader = AirbyteSalesforceReader(config=salesforce_config)
+documents = reader.load_data(stream_name="asset")
+```
+
+## Configuration
+
+Check out the [Airbyte documentation page](https://docs.airbyte.com/integrations/sources/salesforce/) for details about how to configure the reader.
+The JSON schema the config object should adhere to can be found on Github: [https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-salesforce/source_salesforce/spec.yaml](https://github.com/airbytehq/airbyte/blob/master/airbyte-integrations/connectors/source-salesforce/source_salesforce/spec.yaml).
+
+The general shape looks like this:
+```python
+{
+  "client_id": "<oauth client id>",
+  "client_secret": "<oauth client secret>",
+  "refresh_token": "<oauth refresh token>",
+  "start_date": "<date from which to start retrieving records from in ISO format, e.g. 2020-10-20T00:00:00Z>",
+  "is_sandbox": False, # set to True if you're using a sandbox environment
+  "streams_criteria": [ # Array of filters for salesforce objects that should be loadable
+    {"criteria": "exacts", "value": "Account"}, # Exact name of salesforce object
+    {"criteria": "starts with", "value": "Asset"}, # Prefix of the name
+    # Other allowed criteria: ends with, contains, starts not with, ends not with, not contains, not exacts
+  ],
+}
+```
+
+By default all fields are stored as metadata in the documents and the text is set to an empty string. Construct the text of the document by transforming the documents returned by the reader:
+```python
+for doc in documents:
+  doc.text = doc.extra_info["title"]
+```
+
+## Incremental loads
+
+This loader supports loading data incrementally (only returning documents that weren't loaded last time or got updated in the meantime):
+```python
+
+reader = AirbyteSalesforceReader(...so many things...)
+documents = reader.load_data(stream_name="asset")
+current_state = reader.last_state # can be pickled away or stored otherwise
+
+updated_documents = reader.load_data(stream_name="asset", state=current_state) # only loads documents that were updated since last time
+```
+
+This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/jerryjliu/gpt_index/tree/main/gpt_index) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent. See [here](https://github.com/emptycrown/llama-hub/tree/main) for examples.
diff --git a/llama_hub/airbyte_salesforce/__init__.py b/llama_hub/airbyte_salesforce/__init__.py
diff --git a/llama_hub/airbyte_salesforce/base.py b/llama_hub/airbyte_salesforce/base.py
@@ -0,0 +1,21 @@
+from typing import Any, Mapping
+from llama_hub.airbyte_cdk.base import AirbyteCDKReader
+
+
+class AirbyteSalesforceReader(AirbyteCDKReader):
+    """AirbyteSalesforceReader reader.
+
+    Retrieve documents from Salesforce 
+
+    Args:
+        config: The config object for the salesforce source.
+    """
+
+    def __init__(
+        self,
+        config: Mapping[str, Any],
+    ) -> None:
+        """Initialize with parameters."""
+        import source_salesforce
+
+        super().__init__(source_class=source_salesforce.SourceSalesforce, config=config)
diff --git a/llama_hub/airbyte_salesforce/requirements.txt b/llama_hub/airbyte_salesforce/requirements.txt
@@ -0,0 +1 @@
+airbyte-source-salesforce