mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-01 11:02:37 +00:00
docs: raw loader codeblock (#28548)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
Erick Friis
GitHub
@@ -60,6 +60,7 @@ copy-infra:
|
||||
cp package.json $(OUTPUT_NEW_DIR)
|
||||
cp sidebars.js $(OUTPUT_NEW_DIR)
|
||||
cp -r static $(OUTPUT_NEW_DIR)
|
||||
cp -r ../libs/cli/langchain_cli/integration_template $(OUTPUT_NEW_DIR)/src/theme
|
||||
cp yarn.lock $(OUTPUT_NEW_DIR)
|
||||
|
||||
render:
|
||||
@@ -81,6 +82,7 @@ build: install-py-deps generate-files copy-infra render md-sync append-related
|
||||
vercel-build: install-vercel-deps build generate-references
|
||||
rm -rf docs
|
||||
mv $(OUTPUT_NEW_DOCS_DIR) docs
|
||||
cp -r ../libs/cli/langchain_cli/integration_template src/theme
|
||||
rm -rf build
|
||||
mkdir static/api_reference
|
||||
git clone --depth=1 https://github.com/langchain-ai/langchain-api-docs-html.git
|
||||
|
||||
@@ -26,81 +26,193 @@ Examples include [chat models](/docs/concepts/chat_models/),
|
||||
Your integration package will typically implement a subclass of at least one of these
|
||||
components. Expand the tabs below to see details on each.
|
||||
|
||||
<details>
|
||||
<summary>Chat models</summary>
|
||||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
import CodeBlock from '@theme/CodeBlock';
|
||||
|
||||
Refer to the [Custom Chat Model Guide](/docs/how_to/custom_chat_model) guide for
|
||||
detail on a starter chat model [implementation](/docs/how_to/custom_chat_model/#implementation).
|
||||
<Tabs>
|
||||
|
||||
:::tip
|
||||
<TabItem value="chat_models" label="Chat models">
|
||||
|
||||
Refer to the [Custom Chat Model Guide](/docs/how_to/custom_chat_model) guide for
|
||||
detail on a starter chat model [implementation](/docs/how_to/custom_chat_model/#implementation).
|
||||
|
||||
The model from the [Custom Chat Model Guide](/docs/how_to/custom_chat_model) is tested
|
||||
against the standard unit and integration tests in the LangChain Github repository.
|
||||
You can also access that implementation directly from Github
|
||||
[here](https://github.com/langchain-ai/langchain/blob/master/libs/standard-tests/tests/unit_tests/custom_chat_model.py).
|
||||
:::tip
|
||||
|
||||
:::
|
||||
The model from the [Custom Chat Model Guide](/docs/how_to/custom_chat_model) is tested
|
||||
against the standard unit and integration tests in the LangChain Github repository.
|
||||
You can also access that implementation directly from Github
|
||||
[here](https://github.com/langchain-ai/langchain/blob/master/libs/standard-tests/tests/unit_tests/custom_chat_model.py).
|
||||
|
||||
</details>
|
||||
:::
|
||||
|
||||
<details>
|
||||
<summary>Vector stores</summary>
|
||||
<details>
|
||||
<summary>Example chat model code</summary>
|
||||
|
||||
Your vector store implementation will depend on your chosen database technology.
|
||||
`langchain-core` includes a minimal
|
||||
[in-memory vector store](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.in_memory.InMemoryVectorStore.html)
|
||||
that we can use as a guide. You can access the code [here](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/vectorstores/in_memory.py).
|
||||
import ChatModelSource from '../../../../src/theme/integration_template/integration_template/chat_models.py';
|
||||
|
||||
All vector stores must inherit from the [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html)
|
||||
base class. This interface consists of methods for writing, deleting and searching
|
||||
for documents in the vector store.
|
||||
<CodeBlock language="jsx" title="langchain_parrot_link/chat_models.py">
|
||||
{
|
||||
ChatModelSource.replaceAll('__ModuleName__', 'ParrotLink')
|
||||
.replaceAll('__package_name__', 'langchain-parrot-link')
|
||||
.replaceAll('__MODULE_NAME__', 'PARROT_LINK')
|
||||
.replaceAll('__module_name__', 'langchain_parrot_link')
|
||||
}
|
||||
</CodeBlock>
|
||||
|
||||
`VectorStore` supports a variety of synchronous and asynchronous search types (e.g.,
|
||||
nearest-neighbor or maximum marginal relevance), as well as interfaces for adding
|
||||
documents to the store. See the [API Reference](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html)
|
||||
for all supported methods. The required methods are tabulated below:
|
||||
</details>
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="vector_stores" label="Vector stores">
|
||||
|
||||
Your vector store implementation will depend on your chosen database technology.
|
||||
`langchain-core` includes a minimal
|
||||
[in-memory vector store](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.in_memory.InMemoryVectorStore.html)
|
||||
that we can use as a guide. You can access the code [here](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/vectorstores/in_memory.py).
|
||||
|
||||
All vector stores must inherit from the [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html)
|
||||
base class. This interface consists of methods for writing, deleting and searching
|
||||
for documents in the vector store.
|
||||
|
||||
`VectorStore` supports a variety of synchronous and asynchronous search types (e.g.,
|
||||
nearest-neighbor or maximum marginal relevance), as well as interfaces for adding
|
||||
documents to the store. See the [API Reference](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html)
|
||||
for all supported methods. The required methods are tabulated below:
|
||||
|
||||
| Method/Property | Description |
|
||||
|------------------------ |------------------------------------------------------|
|
||||
| `add_documents` | Add documents to the vector store. |
|
||||
| `delete` | Delete selected documents from vector store (by IDs) |
|
||||
| `get_by_ids` | Get selected documents from vector store (by IDs) |
|
||||
| `similarity_search` | Get documents most similar to a query. |
|
||||
| `embeddings` (property) | Embeddings object for vector store. |
|
||||
| `from_texts` | Instantiate vector store via adding texts. |
|
||||
|
||||
Note that `InMemoryVectorStore` implements some optional search types, as well as
|
||||
convenience methods for loading and dumping the object to a file, but this is not
|
||||
necessary for all implementations.
|
||||
|
||||
:::tip
|
||||
|
||||
The [in-memory vector store](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/vectorstores/in_memory.py)
|
||||
is tested against the standard tests in the LangChain Github repository.
|
||||
|
||||
:::
|
||||
|
||||
<details>
|
||||
<summary>Example vector store code</summary>
|
||||
|
||||
import VectorstoreSource from '../../../../src/theme/integration_template/integration_template/vectorstores.py';
|
||||
|
||||
<CodeBlock language="jsx" title="langchain_parrot_link/vectorstores.py">
|
||||
{
|
||||
VectorstoreSource.replaceAll('__ModuleName__', 'ParrotLink')
|
||||
.replaceAll('__package_name__', 'langchain-parrot-link')
|
||||
.replaceAll('__MODULE_NAME__', 'PARROT_LINK')
|
||||
.replaceAll('__module_name__', 'langchain_parrot_link')
|
||||
}
|
||||
</CodeBlock>
|
||||
|
||||
</details>
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="embeddings" label="Embeddings">
|
||||
|
||||
<details>
|
||||
<summary>Example embeddings code</summary>
|
||||
|
||||
Embeddings are used to convert `str` objects from `Document.page_content` fields
|
||||
into a vector representation (represented as a list of floats).
|
||||
|
||||
The `Embeddings` class must inherit from the [Embeddings](https://python.langchain.com/api_reference/core/embeddings/langchain_core.embeddings.embeddings.Embeddings.html#langchain_core.embeddings.embeddings.Embeddings)
|
||||
base class. This interface has 5 methods that can be implemented.
|
||||
|
||||
| Method/Property | Description |
|
||||
|------------------------ |------------------------------------------------------|
|
||||
| `add_documents` | Add documents to the vector store. |
|
||||
| `delete` | Delete selected documents from vector store (by IDs) |
|
||||
| `get_by_ids` | Get selected documents from vector store (by IDs) |
|
||||
| `similarity_search` | Get documents most similar to a query. |
|
||||
| `embeddings` (property) | Embeddings object for vector store. |
|
||||
| `from_texts` | Instantiate vector store via adding texts. |
|
||||
| `__init__` | Initialize the embeddings object. (optional) |
|
||||
| `embed_query` | Embed a list of texts. (required) |
|
||||
| `embed_documents` | Embed a list of documents. (required) |
|
||||
| `aembed_query` | Asynchronously embed a list of texts. (optional) |
|
||||
| `aembed_documents` | Asynchronously embed a list of documents. (optional) |
|
||||
|
||||
Note that `InMemoryVectorStore` implements some optional search types, as well as
|
||||
convenience methods for loading and dumping the object to a file, but this is not
|
||||
necessary for all implementations.
|
||||
### Constructor
|
||||
|
||||
:::tip
|
||||
The `__init__` constructor is optional but common, but can be used to set up any necessary attributes
|
||||
that a user can pass in when initializing the embeddings object. Common attributes include
|
||||
|
||||
The [in-memory vector store](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/vectorstores/in_memory.py)
|
||||
is tested against the standard tests in the LangChain Github repository.
|
||||
- `model` - the id of the model to use for embeddings
|
||||
|
||||
:::
|
||||
### Embedding queries vs documents
|
||||
|
||||
</details>
|
||||
The `embed_query` and `embed_documents` methods are required. These methods both operate
|
||||
on string inputs (the accessing of `Document.page_content` attributes) is handled
|
||||
by the VectorStore using the embedding model for legacy reasons.
|
||||
|
||||
<!-- <details>
|
||||
<summary>Embeddings</summary>
|
||||
`embed_query` takes in a single string and returns a single embedding as a list of floats.
|
||||
If your model has different modes for embedding queries vs the underlying documents, you can
|
||||
implement this method to handle that.
|
||||
|
||||
</details>
|
||||
`embed_documents` takes in a list of strings and returns a list of embeddings as a list of lists of floats.
|
||||
|
||||
<details>
|
||||
<summary>Tools</summary>
|
||||
|
||||
</details>
|
||||
### Async methods
|
||||
|
||||
<details>
|
||||
<summary>Retrievers</summary>
|
||||
|
||||
</details>
|
||||
import EmbeddingsSource from '/src/theme/integration_template/integration_template/embeddings.py';
|
||||
|
||||
<details>
|
||||
<summary>Document Loaders</summary>
|
||||
<CodeBlock language="jsx" title="langchain_parrot_link/embeddings.py">
|
||||
{
|
||||
EmbeddingsSource.replaceAll('__ModuleName__', 'ParrotLink')
|
||||
.replaceAll('__package_name__', 'langchain-parrot-link')
|
||||
.replaceAll('__MODULE_NAME__', 'PARROT_LINK')
|
||||
.replaceAll('__module_name__', 'langchain_parrot_link')
|
||||
}
|
||||
</CodeBlock>
|
||||
|
||||
</details> -->
|
||||
</details>
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="tools" label="Tools">
|
||||
|
||||
<details>
|
||||
<summary>Example tool code</summary>
|
||||
|
||||
import ToolSource from '/src/theme/integration_template/integration_template/tools.py';
|
||||
|
||||
<CodeBlock language="jsx" title="langchain_parrot_link/tools.py">
|
||||
{
|
||||
ToolSource.replaceAll('__ModuleName__', 'ParrotLink')
|
||||
.replaceAll('__package_name__', 'langchain-parrot-link')
|
||||
.replaceAll('__MODULE_NAME__', 'PARROT_LINK')
|
||||
.replaceAll('__module_name__', 'langchain_parrot_link')
|
||||
}
|
||||
</CodeBlock>
|
||||
|
||||
</details>
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="retrievers" label="Retrievers">
|
||||
|
||||
<details>
|
||||
<summary>Example retriever code</summary>
|
||||
|
||||
import RetrieverSource from '/src/theme/integration_template/integration_template/retrievers.py';
|
||||
|
||||
<CodeBlock language="jsx" title="langchain_parrot_link/retrievers.py">
|
||||
{
|
||||
RetrieverSource.replaceAll('__ModuleName__', 'ParrotLink')
|
||||
.replaceAll('__package_name__', 'langchain-parrot-link')
|
||||
.replaceAll('__MODULE_NAME__', 'PARROT_LINK')
|
||||
.replaceAll('__module_name__', 'langchain_parrot_link')
|
||||
}
|
||||
</CodeBlock>
|
||||
|
||||
</details>
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
---
|
||||
|
||||
## (Optional) bootstrapping a new integration package
|
||||
|
||||
|
||||
@@ -35,6 +35,7 @@
|
||||
"json-loader": "^0.5.7",
|
||||
"prism-react-renderer": "^2.1.0",
|
||||
"process": "^0.11.10",
|
||||
"raw-loader": "^4.0.2",
|
||||
"react": "^18",
|
||||
"react-dom": "^18",
|
||||
"typescript": "^5.2.2",
|
||||
|
||||
@@ -9043,6 +9043,14 @@ raw-body@2.5.2:
|
||||
iconv-lite "0.4.24"
|
||||
unpipe "1.0.0"
|
||||
|
||||
raw-loader@^4.0.2:
|
||||
version "4.0.2"
|
||||
resolved "https://registry.yarnpkg.com/raw-loader/-/raw-loader-4.0.2.tgz#1aac6b7d1ad1501e66efdac1522c73e59a584eb6"
|
||||
integrity sha512-ZnScIV3ag9A4wPX/ZayxL/jZH+euYb6FcUinPcgiQW0+UBtEv0O6Q3lGd3cqJ+GHH+rksEv3Pj99oxJ3u3VIKA==
|
||||
dependencies:
|
||||
loader-utils "^2.0.0"
|
||||
schema-utils "^3.0.0"
|
||||
|
||||
rc@1.2.8:
|
||||
version "1.2.8"
|
||||
resolved "https://registry.yarnpkg.com/rc/-/rc-1.2.8.tgz#cd924bf5200a075b83c188cd6b9e211b7fc0d3ed"
|
||||
|
||||
Reference in New Issue
Block a user