Skip to content

Commit 3f09fe9

Browse files
mdrxyCopilot
mdrxy
and
Copilot
authored
oss: nits (#1760)
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
1 parent 34f586a commit 3f09fe9

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

45 files changed

+228
-255
lines changed

‎pipeline/tools/partner_pkg_table.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -191,7 +191,7 @@ def doc() -> str:
191191
{{/* File generated automatically by pipeline/tools/partner_pkg_table.py */}}
192192
{{/* Do not manually edit */}}
193193
194-
LangChain Python offers an extensive ecosystem with 1000+ integrations across chat & embedding models, tools & toolkits, document loaders, vector stores, and more.
194+
LangChain offers an extensive ecosystem with 1000+ integrations across chat & embedding models, tools & toolkits, document loaders, vector stores, and more.
195195
196196
<Columns cols={{3}}>
197197
<Card title="Chat models" icon="message" href="/oss/integrations/chat" arrow />

‎src/docs.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -315,7 +315,7 @@
315315
"oss/python/integrations/providers/huggingface",
316316
"oss/python/integrations/providers/microsoft",
317317
"oss/python/integrations/providers/ollama",
318-
"oss/python/integrations/providers/groq"
318+
"oss/python/integrations/chat/groq"
319319
]
320320
},
321321
{

‎src/langsmith/prompt-commit.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -390,7 +390,7 @@ Now, with everything set up, here's what happens:
390390

391391
6. **Confirmation:** You should see the new commit appear in your GitHub repository.
392392

393-
![Manifest commited to Github](/langsmith/images/prompt-commit-github.png)
393+
![Manifest commited to GitHub](/langsmith/images/prompt-commit-github.png)
394394

395395
You've now successfully synced your LangSmith prompts with GitHub!
396396

‎src/oss/integrations/splitters/index.mdx‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -7,14 +7,14 @@ title: "Text splitters"
77
There are several strategies for splitting documents, each with its own advantages.
88

99
<Tip>
10-
For most use cases, start with the [RecursiveCharacterTextSplitter](/oss/integrations/splitters/recursive_text_splitter). It provides a solid balance between keeping context intact and managing chunk size. This default strategy works well out of the box, and you should only consider adjusting it if you need to fine-tune performance for your specific application.
10+
For most use cases, start with the [`RecursiveCharacterTextSplitter`](/oss/integrations/splitters/recursive_text_splitter). It provides a solid balance between keeping context intact and managing chunk size. This default strategy works well out of the box, and you should only consider adjusting it if you need to fine-tune performance for your specific application.
1111
</Tip>
1212

1313
## Text structure-based
1414

1515
Text is naturally organized into hierarchical units such as paragraphs, sentences, and words. We can leverage this inherent structure to inform our splitting strategy, creating split that maintain natural language flow, maintain semantic coherence within split, and adapts to varying levels of text granularity. LangChain's `RecursiveCharacterTextSplitter` implements this concept:
1616

17-
- The [RecursiveCharacterTextSplitter](/oss/integrations/splitters/recursive_text_splitter) attempts to keep larger units (e.g., paragraphs) intact.
17+
- The [`RecursiveCharacterTextSplitter`](/oss/integrations/splitters/recursive_text_splitter) attempts to keep larger units (e.g., paragraphs) intact.
1818
- If a unit exceeds the chunk size, it moves to the next level (e.g., sentences).
1919
- This process continues down to the word level if necessary.
2020

@@ -53,7 +53,7 @@ Types of length-based splitting:
5353
- Token-based: Splits text based on the number of tokens, which is useful when working with language models.
5454
- Character-based: Splits text based on the number of characters, which can be more consistent across different types of text.
5555

56-
Example implementation using LangChain's CharacterTextSplitter with token-based splitting:
56+
Example implementation using LangChain's `CharacterTextSplitter` with token-based splitting:
5757

5858
:::python
5959
```python
@@ -89,7 +89,7 @@ Some documents have an inherent structure, such as HTML, Markdown, or JSON files
8989
:::python
9090
Examples of structure-based splitting:
9191

92-
- Markdown: Split based on headers (e.g., #, ##, ###)
92+
- Markdown: Split based on headers (e.g., `#`, `##`, `###`)
9393
- HTML: Split using tags
9494
- JSON: Split by object or array elements
9595
- Code: Split by functions, classes, or logical blocks

‎src/oss/javascript/integrations/document_loaders/index.mdx‎

Lines changed: 17 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -12,8 +12,8 @@ All document loaders implement the @[BaseLoader] interface.
1212

1313
Each document loader may define its own parameters, but they share a common API:
1414

15-
- `.load()`: Loads all documents at once.
16-
- `.loadAndSplit()`: Loads all documents at once and splits them into smaller documents.
15+
- `load()`: Loads all documents at once.
16+
- `loadAndSplit()`: Loads all documents at once and splits them into smaller documents.
1717

1818
```typescript
1919
import { CSVLoader } from "@langchain/community/document_loaders/fs/csv";
@@ -43,7 +43,7 @@ LangChain.js categorizes document loaders in two different ways:
4343
|----------------|-------------|-------------|
4444
| [PDFLoader](/oss/integrations/document_loaders/file_loaders/pdf) | Load and parse PDF files using pdf-parse | Package |
4545

46-
#### Common File Types
46+
#### Common file types
4747

4848
| Document Loader | Description | Package/API |
4949
|----------------|-------------|-------------|
@@ -56,14 +56,14 @@ LangChain.js categorizes document loaders in two different ways:
5656
| [PPTX](/oss/integrations/document_loaders/file_loaders/pptx) | Load PowerPoint presentations | Package |
5757
| [Subtitles](/oss/integrations/document_loaders/file_loaders/subtitles) | Load subtitle files (.srt format) | Package |
5858

59-
#### Specialized File Loaders
59+
#### Specialized file loaders
6060

6161
| Document Loader | Description | Package/API |
6262
|----------------|-------------|-------------|
63-
| [DirectoryLoader](/oss/integrations/document_loaders/file_loaders/directory) | Load all files from a directory with custom loader mappings | Package |
64-
| [UnstructuredLoader](/oss/integrations/document_loaders/file_loaders/unstructured) | Load multiple file types using Unstructured API | API |
65-
| [MultiFileLoader](/oss/integrations/document_loaders/file_loaders/multi_file) | Load data from multiple individual file paths | Package |
66-
| [ChatGPT](/oss/integrations/document_loaders/file_loaders/chatgpt) | Load ChatGPT conversation exports | Package |
63+
| [`DirectoryLoader`](/oss/integrations/document_loaders/file_loaders/directory) | Load all files from a directory with custom loader mappings | Package |
64+
| [`UnstructuredLoader`](/oss/integrations/document_loaders/file_loaders/unstructured) | Load multiple file types using Unstructured API | API |
65+
| [`MultiFileLoader`](/oss/integrations/document_loaders/file_loaders/multi_file) | Load data from multiple individual file paths | Package |
66+
| [`ChatGPT`](/oss/integrations/document_loaders/file_loaders/chatgpt) | Load ChatGPT conversation exports | Package |
6767
| [Notion Markdown](/oss/integrations/document_loaders/file_loaders/notion_markdown) | Load Notion pages exported as Markdown | Package |
6868
| [OpenAI Whisper Audio](/oss/integrations/document_loaders/file_loaders/openai_whisper_audio) | Transcribe audio files using OpenAI Whisper API | API |
6969

@@ -73,15 +73,15 @@ LangChain.js categorizes document loaders in two different ways:
7373

7474
| Document Loader | Description | Web Support | Package/API |
7575
|----------------|-------------|:-----------:|-------------|
76-
| [Cheerio](/oss/integrations/document_loaders/web_loaders/web_cheerio) | Load webpages using Cheerio (lightweight, no JavaScript execution) | ✅ | Package |
77-
| [Playwright](/oss/integrations/document_loaders/web_loaders/web_playwright) | Load dynamic webpages using Playwright (supports JavaScript rendering) | ❌ | Package |
78-
| [Puppeteer](/oss/integrations/document_loaders/web_loaders/web_puppeteer) | Load dynamic webpages using Puppeteer (headless Chrome) | ❌ | Package |
79-
| [FireCrawl](/oss/integrations/document_loaders/web_loaders/firecrawl) | Crawl and convert websites into LLM-ready markdown | ✅ | API |
80-
| [Spider](/oss/integrations/document_loaders/web_loaders/spider) | Fast crawler that converts websites into HTML, markdown, or text | ✅ | API |
81-
| [RecursiveUrlLoader](/oss/integrations/document_loaders/web_loaders/recursive_url_loader) | Recursively load webpages following links | ❌ | Package |
82-
| [Sitemap](/oss/integrations/document_loaders/web_loaders/sitemap) | Load all pages from a sitemap.xml | ✅ | Package |
83-
| [Browserbase](/oss/integrations/document_loaders/web_loaders/browserbase) | Load webpages using managed headless browsers with stealth mode | ✅ | API |
84-
| [WebPDFLoader](/oss/integrations/document_loaders/web_loaders/pdf) | Load PDF files in web environments | ✅ | Package |
76+
| [`Cheerio`](/oss/integrations/document_loaders/web_loaders/web_cheerio) | Load webpages using Cheerio (lightweight, no JavaScript execution) | ✅ | Package |
77+
| [`Playwright`](/oss/integrations/document_loaders/web_loaders/web_playwright) | Load dynamic webpages using Playwright (supports JavaScript rendering) | ❌ | Package |
78+
| [`Puppeteer`](/oss/integrations/document_loaders/web_loaders/web_puppeteer) | Load dynamic webpages using Puppeteer (headless Chrome) | ❌ | Package |
79+
| [`FireCrawl`](/oss/integrations/document_loaders/web_loaders/firecrawl) | Crawl and convert websites into LLM-ready markdown | ✅ | API |
80+
| [`Spider`](/oss/integrations/document_loaders/web_loaders/spider) | Fast crawler that converts websites into HTML, markdown, or text | ✅ | API |
81+
| [`RecursiveUrlLoader`](/oss/integrations/document_loaders/web_loaders/recursive_url_loader) | Recursively load webpages following links | ❌ | Package |
82+
| [`Sitemap`](/oss/integrations/document_loaders/web_loaders/sitemap) | Load all pages from a sitemap.xml | ✅ | Package |
83+
| [`Browserbase`](/oss/integrations/document_loaders/web_loaders/browserbase) | Load webpages using managed headless browsers with stealth mode | ✅ | API |
84+
| [`WebPDFLoader`](/oss/integrations/document_loaders/web_loaders/pdf) | Load PDF files in web environments | ✅ | Package |
8585

8686
#### Cloud Providers
8787

‎src/oss/javascript/integrations/retrievers/index.mdx‎

Lines changed: 114 additions & 114 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ A [retriever](/oss/langchain/retrieval) is an interface that returns documents g
66
It is more general than a vector store.
77
A retriever does not need to be able to store documents, only to return (or retrieve) them.
88

9-
Retrievers accept a string query as input and return a list of Documents.
9+
Retrievers accept a string query as input and return a list of `Document` objects.
1010

1111
For specifics on how to use retrievers, see the [relevant how-to guides here](/oss/langchain/retrieval).
1212

@@ -16,125 +16,125 @@ Refer to the vector store [integration docs](/oss/integrations/vectorstores/) fo
1616
## All retrievers
1717

1818
<Columns cols={3}>
19-
<Card
20-
title="Alchemyst AI Retriever"
21-
icon="link"
22-
href="/oss/integrations/retrievers/alchemystai-retriever"
23-
arrow="true"
24-
cta="View guide"
25-
/>
26-
<Card
27-
title="ArxivRetriever"
28-
icon="link"
29-
href="/oss/integrations/retrievers/arxiv-retriever"
30-
arrow="true"
31-
cta="View guide"
32-
/>
33-
<Card
34-
title="Azion EdgeSQL"
35-
icon="link"
36-
href="/oss/integrations/retrievers/azion-edgesql"
37-
arrow="true"
38-
cta="View guide"
39-
/>
40-
<Card
41-
title="Knowledge Bases for Amazon Bedrock"
42-
icon="link"
43-
href="/oss/integrations/retrievers/bedrock-knowledge-bases"
44-
arrow="true"
45-
cta="View guide"
46-
/>
47-
<Card
48-
title="BM25"
49-
icon="link"
50-
href="/oss/integrations/retrievers/bm25"
51-
arrow="true"
52-
cta="View guide"
53-
/>
54-
<Card
55-
title="Chaindesk Retriever"
56-
icon="link"
57-
href="/oss/integrations/retrievers/chaindesk-retriever"
58-
arrow="true"
59-
cta="View guide"
60-
/>
61-
<Card
62-
title="Dria Retriever"
63-
icon="link"
64-
href="/oss/integrations/retrievers/dria"
65-
arrow="true"
66-
cta="View guide"
67-
/>
68-
<Card
69-
title="Exa"
70-
icon="link"
71-
href="/oss/integrations/retrievers/exa"
72-
arrow="true"
73-
cta="View guide"
74-
/>
75-
<Card
76-
title="HyDE Retriever"
77-
icon="link"
78-
href="/oss/integrations/retrievers/hyde"
79-
arrow="true"
80-
cta="View guide"
81-
/>
82-
<Card
83-
title="Amazon Kendra Retriever"
84-
icon="link"
85-
href="/oss/integrations/retrievers/kendra-retriever"
86-
arrow="true"
87-
cta="View guide"
88-
/>
89-
<Card
90-
title="Metal Retriever"
91-
icon="link"
92-
href="/oss/integrations/retrievers/metal-retriever"
93-
arrow="true"
94-
cta="View guide"
19+
<Card
20+
title="Alchemyst AI Retriever"
21+
icon="link"
22+
href="/oss/integrations/retrievers/alchemystai-retriever"
23+
arrow="true"
24+
cta="View guide"
9525
/>
96-
<Card
97-
title="Supabase Hybrid Search"
98-
icon="link"
99-
href="/oss/integrations/retrievers/supabase-hybrid"
100-
arrow="true"
101-
cta="View guide"
26+
<Card
27+
title="ArxivRetriever"
28+
icon="link"
29+
href="/oss/integrations/retrievers/arxiv-retriever"
30+
arrow="true"
31+
cta="View guide"
10232
/>
103-
<Card
104-
title="Tavily Search API"
105-
icon="link"
106-
href="/oss/integrations/retrievers/tavily"
107-
arrow="true"
108-
cta="View guide"
33+
<Card
34+
title="Azion EdgeSQL"
35+
icon="link"
36+
href="/oss/integrations/retrievers/azion-edgesql"
37+
arrow="true"
38+
cta="View guide"
10939
/>
110-
<Card
111-
title="Time-Weighted Retriever"
112-
icon="link"
113-
href="/oss/integrations/retrievers/time-weighted-retriever"
114-
arrow="true"
115-
cta="View guide"
40+
<Card
41+
title="Knowledge Bases for Amazon Bedrock"
42+
icon="link"
43+
href="/oss/integrations/retrievers/bedrock-knowledge-bases"
44+
arrow="true"
45+
cta="View guide"
11646
/>
117-
<Card
118-
title="Vespa Retriever"
119-
icon="link"
120-
href="/oss/integrations/retrievers/vespa-retriever"
121-
arrow="true"
122-
cta="View guide"
47+
<Card
48+
title="BM25"
49+
icon="link"
50+
href="/oss/integrations/retrievers/bm25"
51+
arrow="true"
52+
cta="View guide"
12353
/>
124-
<Card
125-
title="Zep Cloud Retriever"
126-
icon="link"
127-
href="/oss/integrations/retrievers/zep-cloud-retriever"
128-
arrow="true"
129-
cta="View guide"
54+
<Card
55+
title="Chaindesk Retriever"
56+
icon="link"
57+
href="/oss/integrations/retrievers/chaindesk-retriever"
58+
arrow="true"
59+
cta="View guide"
60+
/>
61+
<Card
62+
title="Dria Retriever"
63+
icon="link"
64+
href="/oss/integrations/retrievers/dria"
65+
arrow="true"
66+
cta="View guide"
67+
/>
68+
<Card
69+
title="Exa"
70+
icon="link"
71+
href="/oss/integrations/retrievers/exa"
72+
arrow="true"
73+
cta="View guide"
74+
/>
75+
<Card
76+
title="HyDE Retriever"
77+
icon="link"
78+
href="/oss/integrations/retrievers/hyde"
79+
arrow="true"
80+
cta="View guide"
81+
/>
82+
<Card
83+
title="Amazon Kendra Retriever"
84+
icon="link"
85+
href="/oss/integrations/retrievers/kendra-retriever"
86+
arrow="true"
87+
cta="View guide"
88+
/>
89+
<Card
90+
title="Metal Retriever"
91+
icon="link"
92+
href="/oss/integrations/retrievers/metal-retriever"
93+
arrow="true"
94+
cta="View guide"
95+
/>
96+
<Card
97+
title="Supabase Hybrid Search"
98+
icon="link"
99+
href="/oss/integrations/retrievers/supabase-hybrid"
100+
arrow="true"
101+
cta="View guide"
102+
/>
103+
<Card
104+
title="Tavily Search API"
105+
icon="link"
106+
href="/oss/integrations/retrievers/tavily"
107+
arrow="true"
108+
cta="View guide"
109+
/>
110+
<Card
111+
title="Time-Weighted Retriever"
112+
icon="link"
113+
href="/oss/integrations/retrievers/time-weighted-retriever"
114+
arrow="true"
115+
cta="View guide"
116+
/>
117+
<Card
118+
title="Vespa Retriever"
119+
icon="link"
120+
href="/oss/integrations/retrievers/vespa-retriever"
121+
arrow="true"
122+
cta="View guide"
123+
/>
124+
<Card
125+
title="Zep Cloud Retriever"
126+
icon="link"
127+
href="/oss/integrations/retrievers/zep-cloud-retriever"
128+
arrow="true"
129+
cta="View guide"
130+
/>
131+
<Card
132+
title="Zep Open Source Retriever"
133+
icon="link"
134+
href="/oss/integrations/retrievers/zep-retriever"
135+
arrow="true"
136+
cta="View guide"
130137
/>
131-
<Card
132-
title="Zep Open Source Retriever"
133-
icon="link"
134-
href="/oss/integrations/retrievers/zep-retriever"
135-
arrow="true"
136-
cta="View guide"
137-
/>
138138
</Columns>
139139

140140
<Info>

‎src/oss/langchain/models.mdx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1257,7 +1257,7 @@ Model profile data allow applications to work around model capabilities dynamica
12571257
12581258
Model profile data can be updated through the following process:
12591259
1260-
1. (If needed) update the source data at [models.dev](https://models.dev/) through a pull request to its [repository on Github](https://github.com/sst/models.dev).
1260+
1. (If needed) update the source data at [models.dev](https://models.dev/) through a pull request to its [repository on GitHub](https://github.com/sst/models.dev).
12611261
2. (If needed) update additional fields and overrides in `langchain_<package>/data/profile_augmentations.toml` through a pull request to the LangChain [integration package](/oss/integrations/providers/overview)`.
12621262
3. Use the [`langchain-model-profiles`](https://pypi.org/project/langchain-model-profiles/) CLI tool to pull the latest data from [models.dev](https://models.dev/), merge in the augmentations and update the profile data:
12631263

@@ -1330,7 +1330,7 @@ Model profile data allow applications to work around model capabilities dynamica
13301330

13311331
Model profile data can be updated through the following process:
13321332

1333-
1. (If needed) update the source data at [models.dev](https://models.dev/) through a pull request to its [repository on Github](https://github.com/sst/models.dev).
1333+
1. (If needed) update the source data at [models.dev](https://models.dev/) through a pull request to its [repository on GitHub](https://github.com/sst/models.dev).
13341334
2. (If needed) update additional fields and overrides in `langchain-<package>/profiles.toml` through a pull request to the LangChain [integration package](/oss/integrations/providers/overview).
13351335
</Accordion>
13361336

‎src/oss/python/integrations/callbacks/confident.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -151,4 +151,4 @@ You can create your own custom metrics [here](https://docs.confident-ai.com/docs
151151

152152
DeepEval also offers other features such as being able to [automatically create unit tests](https://docs.confident-ai.com/docs/quickstart/synthetic-data-creation), [tests for hallucination](https://docs.confident-ai.com/docs/measuring_llm_performance/factual_consistency).
153153

154-
If you are interested, check out our Github repository here [https://github.com/confident-ai/deepeval](https://github.com/confident-ai/deepeval). We welcome any PRs and discussions on how to improve LLM performance.
154+
If you are interested, check out our GitHub repository here [https://github.com/confident-ai/deepeval](https://github.com/confident-ai/deepeval). We welcome any PRs and discussions on how to improve LLM performance.

0 commit comments

Comments
 (0)