Skip to content

The agent engineering platform.

docs: `integrations` reference updates 13 (#25711)

Leonid Ganeline150251fd4987
diff --git a/docs/docs/integrations/providers/falkordb.mdx b/docs/docs/integrations/providers/falkordb.mdx
new file mode 100644
index 0000000000..66afc5522e
--- /dev/null
+++ b/docs/docs/integrations/providers/falkordb.mdx
@@ -0,0 +1,26 @@
+# FalkorDB
+
+>[FalkorDB](https://www.falkordb.com/) is a creator of the [FalkorDB](https://docs.falkordb.com/),
+> a low-latency Graph Database that delivers knowledge to GenAI.
+
+
+## Installation and Setup
+
+See [installation instructions here](/docs/integrations/graphs/falkordb/).
+
+
+## Graphs
+
+See a [usage example](/docs/integrations/graphs/falkordb).
+
+```python
+from langchain_community.graphs import FalkorDBGraph
+```
+
+## Chains
+
+See a [usage example](/docs/integrations/graphs/falkordb).
+
+```python
+from langchain_community.chains.graph_qa.falkordb import FalkorDBQAChain
+```
diff --git a/docs/docs/integrations/providers/firecrawl.mdx b/docs/docs/integrations/providers/firecrawl.mdx
new file mode 100644
index 0000000000..bbee26ceed
--- /dev/null
+++ b/docs/docs/integrations/providers/firecrawl.mdx
@@ -0,0 +1,22 @@
+# FireCrawl
+
+>[FireCrawl](https://firecrawl.dev/?ref=langchain) crawls and converts any website into LLM-ready data.
+> It crawls all accessible subpages and give you clean markdown
+> and metadata for each. No sitemap required.
+
+
+## Installation and Setup
+
+Install the python SDK:
+
+```bash
+pip install firecrawl-py
+```
+
+## Document loader
+
+See a [usage example](/docs/integrations/document_loaders/firecrawl).
+
+```python
+from langchain_community.document_loaders import FireCrawlLoader
+```
diff --git a/docs/docs/integrations/providers/friendly.md b/docs/docs/integrations/providers/friendly.md
new file mode 100644
index 0000000000..834a1ebfe8
--- /dev/null
+++ b/docs/docs/integrations/providers/friendly.md
@@ -0,0 +1,32 @@
+# Friendli AI
+
+>[Friendli AI](https://friendli.ai/) is a company that fine-tunes, deploys LLMs,
+> and serves a wide range of Generative AI use cases.
+
+
+## Installation and setup
+
+- Install the integration package:
+
+ ```
+ pip install friendli-client
+ ```
+
+- Sign in to [Friendli Suite](https://suite.friendli.ai/) to create a Personal Access Token,
+and set it as the `FRIENDLI_TOKEN` environment.
+
+## Chat models
+
+See a [usage example](/docs/integrations/chat/friendli).
+
+```python
+from langchain_community.chat_models.friendli import ChatFriendli
+```
+
+## LLMs
+
+See a [usage example](/docs/integrations/llms/friendli).
+
+```python
+from langchain_community.llms.friendli import Friendli
+```
diff --git a/docs/docs/integrations/providers/qdrant.mdx b/docs/docs/integrations/providers/qdrant.mdx
index 021f73d33f..ad047ce072 100644
--- a/docs/docs/integrations/providers/qdrant.mdx
+++ b/docs/docs/integrations/providers/qdrant.mdx
@@ -13,6 +13,19 @@ Install the Python partner package:
pip install langchain-qdrant
```
+## Embedding models
+
+### FastEmbedSparse
+
+```python
+from langchain_qdrant import FastEmbedSparse
+```
+
+### SparseEmbeddings
+
+```python
+from langchain_qdrant import SparseEmbeddings
+```
## Vector Store
diff --git a/docs/docs/integrations/vectorstores/faiss.ipynb b/docs/docs/integrations/vectorstores/faiss.ipynb
index 1cc19a9b2c..6010694698 100644
--- a/docs/docs/integrations/vectorstores/faiss.ipynb
+++ b/docs/docs/integrations/vectorstores/faiss.ipynb
@@ -7,7 +7,9 @@
"source": [
"# Faiss\n",
"\n",
- ">[Facebook AI Similarity Search (FAISS)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
+ ">[Facebook AI Similarity Search (FAISS)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also includes supporting code for evaluation and parameter tuning.\n",
+ ">\n",
+ ">See [The FAISS Library](https://arxiv.org/pdf/2401.08281) paper.\n",
"\n",
"You can find the FAISS documentation at [this page](https://faiss.ai/).\n",
"\n",
@@ -528,7 +530,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.9"
+ "version": "3.10.12"
}
},
"nbformat": 4,
diff --git a/docs/docs/integrations/vectorstores/faiss_async.ipynb b/docs/docs/integrations/vectorstores/faiss_async.ipynb
index 770f8b78e0..8c248e427e 100644
--- a/docs/docs/integrations/vectorstores/faiss_async.ipynb
+++ b/docs/docs/integrations/vectorstores/faiss_async.ipynb
@@ -7,7 +7,9 @@
"source": [
"# Faiss (Async)\n",
"\n",
- ">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
+ ">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also includes supporting code for evaluation and parameter tuning.\n",
+ ">\n",
+ ">See [The FAISS Library](https://arxiv.org/pdf/2401.08281) paper.\n",
"\n",
"[Faiss documentation](https://faiss.ai/).\n",
"\n",
diff --git a/libs/community/langchain_community/embeddings/fastembed.py b/libs/community/langchain_community/embeddings/fastembed.py
index ac7253c21e..3a0940c866 100644
--- a/libs/community/langchain_community/embeddings/fastembed.py
+++ b/libs/community/langchain_community/embeddings/fastembed.py
@@ -12,6 +12,7 @@ MIN_VERSION = "0.2.0"
class FastEmbedEmbeddings(BaseModel, Embeddings):
"""Qdrant FastEmbedding models.
+
FastEmbed is a lightweight, fast, Python library built for embedding generation.
See more documentation at:
* https://github.com/qdrant/fastembed/
diff --git a/libs/community/langchain_community/vectorstores/faiss.py b/libs/community/langchain_community/vectorstores/faiss.py
index d6aacb2e36..48225888e5 100644
--- a/libs/community/langchain_community/vectorstores/faiss.py
+++ b/libs/community/langchain_community/vectorstores/faiss.py
@@ -74,6 +74,8 @@ def _len_check_if_sized(x: Any, y: Any, x_name: str, y_name: str) -> None:
class FAISS(VectorStore):
"""FAISS vector store integration.
+ See [The FAISS Library](https://arxiv.org/pdf/2401.08281) paper.
+
Setup:
Install ``langchain_community`` and ``faiss-cpu`` python packages.
diff --git a/libs/langchain/langchain/chains/flare/base.py b/libs/langchain/langchain/chains/flare/base.py
index 1d55bed468..53f3dd1e40 100644
--- a/libs/langchain/langchain/chains/flare/base.py
+++ b/libs/langchain/langchain/chains/flare/base.py
@@ -73,7 +73,10 @@ def _low_confidence_spans(
class FlareChain(Chain):
"""Chain that combines a retriever, a question generator,
- and a response generator."""
+ and a response generator.
+
+ See [Active Retrieval Augmented Generation](https://arxiv.org/abs/2305.06983) paper.
+ """
question_generator_chain: Runnable
"""Chain that generates questions from uncertain spans."""
diff --git a/templates/rag-aws-bedrock/README.md b/templates/rag-aws-bedrock/README.md
index a1bce7dcdd..5d3afae72b 100644
--- a/templates/rag-aws-bedrock/README.md
+++ b/templates/rag-aws-bedrock/README.md
@@ -1,10 +1,12 @@
-# RAG - AWS Bedrock
+# RAG - AWS Bedrock, FAISS
This template is designed to connect with the `AWS Bedrock` service, a managed server that offers a set of foundation models.
It primarily uses the `Anthropic Claude` for text generation and `Amazon Titan` for text embedding, and utilizes FAISS as the vectorstore.
-For additional context on the RAG pipeline, refer to [this notebook](https://github.com/aws-samples/amazon-bedrock-workshop/blob/main/03_QuestionAnswering/01_qa_w_rag_claude.ipynb).
+For additional context on the RAG pipeline, refer to [these notebooks](https://github.com/aws-samples/amazon-bedrock-workshop/tree/main/02_KnowledgeBases_and_RAG).
+
+See [The FAISS Library](https://arxiv.org/pdf/2401.08281) paper for more details.
## Environment Setup