docs: add vLLM embedder documentation

_snippets/embedder-vllm-reference.mdx

@@ -0,0 +1,12 @@
+| Parameter | Type | Description | Default |
+|-----------|------|-------------|---------|
+| `id` | `str` | Model identifier (HuggingFace model name) | `"intfloat/e5-mistral-7b-instruct"` |
+| `dimensions` | `int` | Embedding vector dimensions | `4096` |
+| `base_url` | `Optional[str]` | Remote vLLM server URL (enables remote mode) | `None` |
+| `api_key` | `Optional[str]` | API key for remote server authentication | `getenv("VLLM_API_KEY")` |
+| `enable_batch` | `bool` | Enable batch processing for multiple texts | `False` |
+| `batch_size` | `int` | Number of texts to process per batch | `10` |
+| `enforce_eager` | `bool` | Use eager execution mode (local mode) | `True` |
+| `vllm_kwargs` | `Optional[Dict[str, Any]]` | Additional vLLM engine parameters (local mode) | `None` |
+| `request_params` | `Optional[Dict[str, Any]]` | Additional request parameters (remote mode) | `None` |
+| `client_params` | `Optional[Dict[str, Any]]` | OpenAI client configuration (remote mode) | `None` |

concepts/knowledge/embedder/vllm.mdx

@@ -0,0 +1,89 @@
+---
+title: vLLM Embedder
+sidebarTitle: vLLM
+---
+
+The vLLM Embedder provides high-performance embedding inference with support for both local and remote deployment modes. All models are downloaded from HuggingFace.
+
+## Usage
+
+### Local Mode
+
+You can directly load local models using the vLLM library, without any need to host a model on a server.
+
+```python vllm_embedder.py
+from agno.knowledge.embedder.vllm import VLLMEmbedder
+from agno.knowledge.knowledge import Knowledge
+from agno.vectordb.pgvector import PgVector
+
+# Get embeddings directly
+embeddings = VLLMEmbedder(
+    id="intfloat/e5-mistral-7b-instruct",
+    dimensions=4096,
+    enforce_eager=True,
+    vllm_kwargs={
+        "disable_sliding_window": True,
+        "max_model_len": 4096,
+    },
+).get_embedding("The quick brown fox jumps over the lazy dog.")
+
+print(f"Embeddings: {embeddings[:5]}")
+print(f"Dimensions: {len(embeddings)}")
+
+# Use with Knowledge
+knowledge = Knowledge(
+    vector_db=PgVector(
+        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
+        table_name="vllm_embeddings",
+        embedder=VLLMEmbedder(
+            id="intfloat/e5-mistral-7b-instruct",
+            dimensions=4096,
+            enforce_eager=True,
+            vllm_kwargs={
+                "disable_sliding_window": True,
+                "max_model_len": 4096,
+            },
+        ),
+    ),
+    max_results=2,
+)
+```
+
+### Remote Mode
+
+You can connect to a running vLLM server via an OpenAI-compatible API.
+
+```python vllm_embedder_remote.py
+# Remote mode (for production deployments)
+knowledge_remote = Knowledge(
+    vector_db=PgVector(
+        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
+        table_name="vllm_embeddings_remote",
+        embedder=VLLMEmbedder(
+            id="intfloat/e5-mistral-7b-instruct",
+            dimensions=4096,
+            base_url="http://localhost:8000/v1",  # Example endpoint for local development
+            api_key="your-api-key",  # Optional
+        ),
+    ),
+    max_results=2,
+)
+```
+
+## Params
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `id` | `str` | `"intfloat/e5-mistral-7b-instruct"` | Model identifier (HuggingFace model name) |
+| `dimensions` | `int` | `4096` | Embedding vector dimensions |
+| `base_url` | `Optional[str]` | `None` | Remote vLLM server URL (enables remote mode) |
+| `api_key` | `Optional[str]` | `getenv("VLLM_API_KEY")` | API key for remote server authentication |
+| `enable_batch` | `bool` | `False` | Enable batch processing for multiple texts |
+| `batch_size` | `int` | `10` | Number of texts to process per batch |
+| `enforce_eager` | `bool` | `True` | Use eager execution mode (local mode) |
+| `vllm_kwargs` | `Optional[Dict[str, Any]]` | `None` | Additional vLLM engine parameters (local mode) |
+| `request_params` | `Optional[Dict[str, Any]]` | `None` | Additional request parameters (remote mode) |
+| `client_params` | `Optional[Dict[str, Any]]` | `None` | OpenAI client configuration (remote mode) |
+
+## Developer Resources
+- View [Cookbook](https://github.com/agno-agi/agno/tree/main/cookbook/knowledge/embedders/vllm_embedder.py)

docs.json

@@ -333,6 +333,7 @@
                           "concepts/knowledge/embedder/qdrant_fastembed",
                           "concepts/knowledge/embedder/sentencetransformers",
                           "concepts/knowledge/embedder/together",
+                          "concepts/knowledge/embedder/vllm",
                           "concepts/knowledge/embedder/voyageai",
                           "concepts/knowledge/embedder/aws_bedrock"
                         ]
@@ -1639,6 +1640,7 @@
                       "examples/concepts/knowledge/embedders/nebius-embedder",
                       "examples/concepts/knowledge/embedders/sentence-transformer-embedder",
                       "examples/concepts/knowledge/embedders/together-embedder",
+                      "examples/concepts/knowledge/embedders/vllm-embedder",
                       "examples/concepts/knowledge/embedders/voyageai-embedder"
                     ]
                   },
@@ -2996,6 +2998,7 @@
                       "reference/knowledge/embedder/openai",
                       "reference/knowledge/embedder/sentence-transformer",
                       "reference/knowledge/embedder/together",
+                      "reference/knowledge/embedder/vllm",
                       "reference/knowledge/embedder/voyageai"
                     ]
                   },

examples/concepts/knowledge/embedders/vllm-embedder.mdx

@@ -0,0 +1,119 @@
+---
+title: vLLM Embedder
+---
+
+## Code
+
+```python vllm_embedder.py
+import asyncio
+
+from agno.knowledge.embedder.vllm import VLLMEmbedder
+from agno.knowledge.knowledge import Knowledge
+from agno.vectordb.pgvector import PgVector
+
+
+def main():
+    # Basic usage - get embeddings directly
+    embeddings = VLLMEmbedder(
+        id="intfloat/e5-mistral-7b-instruct",
+        dimensions=4096,
+        enforce_eager=True,
+        vllm_kwargs={
+            "disable_sliding_window": True,
+            "max_model_len": 4096,
+        },
+    ).get_embedding("The quick brown fox jumps over the lazy dog.")
+
+    # Print the embeddings and their dimensions
+    print(f"Embeddings: {embeddings[:5]}")
+    print(f"Dimensions: {len(embeddings)}")
+
+    # Local Mode with Knowledge
+    knowledge = Knowledge(
+        vector_db=PgVector(
+            db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
+            table_name="vllm_embeddings",
+            embedder=VLLMEmbedder(
+                id="intfloat/e5-mistral-7b-instruct",
+                dimensions=4096,
+                enforce_eager=True,
+                vllm_kwargs={
+                    "disable_sliding_window": True,
+                    "max_model_len": 4096,
+                },
+            ),
+        ),
+        max_results=2,
+    )
+
+    # Remote mode with Knowledge
+    knowledge_remote = Knowledge(
+        vector_db=PgVector(
+            db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
+            table_name="vllm_embeddings_remote",
+            embedder=VLLMEmbedder(
+                id="intfloat/e5-mistral-7b-instruct",
+                dimensions=4096,
+                base_url="http://localhost:8000/v1",
+                api_key="your-api-key",  # Optional
+            ),
+        ),
+        max_results=2,
+    )
+
+    asyncio.run(
+        knowledge.add_content_async(
+            path="cookbook/knowledge/testing_resources/cv_1.pdf",
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()
+```
+
+## Usage
+
+<Steps>
+  <Snippet file="create-venv-step.mdx" />
+
+  <Step title="Install libraries">
+    ```bash
+    pip install -U agno vllm openai sqlalchemy psycopg[binary] pgvector pypdf
+    ```
+  </Step>
+
+  <Step title="Run PgVector">
+    ```bash
+    docker run -d \
+      -e POSTGRES_DB=ai \
+      -e POSTGRES_USER=ai \
+      -e POSTGRES_PASSWORD=ai \
+      -e PGDATA=/var/lib/postgresql/data/pgdata \
+      -v pgvolume:/var/lib/postgresql/data \
+      -p 5532:5432 \
+      --name pgvector \
+      agno/pgvector:16
+    ```
+  </Step>
+
+  <Step title="Run the example">
+    <CodeGroup>
+    ```bash Mac
+    python vllm_embedder.py
+    ```
+
+    ```bash Windows
+    python vllm_embedder.py
+    ```
+    </CodeGroup>
+  </Step>
+</Steps>
+
+## Notes
+
+- This example uses **local mode** where vLLM loads the model directly (no server needed)
+- For **remote mode**, the code includes `knowledge_remote` example with `base_url` parameter
+- GPU with ~14GB VRAM required for e5-mistral-7b-instruct model
+- For CPU-only or lower memory, use smaller models like `BAAI/bge-small-en-v1.5`
+- Models are automatically downloaded from HuggingFace on first use

reference/knowledge/embedder/vllm.mdx

@@ -0,0 +1,51 @@
+---
+title: vLLM
+---
+
+The vLLM Embedder provides high-performance embedding inference with support for both local and remote deployment modes. It can load models directly for local inference or connect to a remote vLLM server via an OpenAI-compatible API.
+
+## Usage
+
+```python
+from agno.knowledge.embedder.vllm import VLLMEmbedder
+from agno.knowledge.knowledge import Knowledge
+from agno.vectordb.pgvector import PgVector
+
+# Local mode
+embedder = VLLMEmbedder(
+    id="intfloat/e5-mistral-7b-instruct",
+    dimensions=4096,
+    enforce_eager=True,
+    vllm_kwargs={
+        "disable_sliding_window": True,
+        "max_model_len": 4096,
+    },
+)
+
+# Use with Knowledge
+knowledge = Knowledge(
+    vector_db=PgVector(
+        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
+        table_name="vllm_embeddings",
+        embedder=embedder,
+    ),
+)
+```
+
+## Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `id` | `str` | `"intfloat/e5-mistral-7b-instruct"` | Model identifier (HuggingFace model name) |
+| `dimensions` | `int` | `4096` | Embedding vector dimensions |
+| `base_url` | `Optional[str]` | `None` | Remote vLLM server URL (enables remote mode) |
+| `api_key` | `Optional[str]` | `getenv("VLLM_API_KEY")` | API key for remote server authentication |
+| `enable_batch` | `bool` | `False` | Enable batch processing for multiple texts |
+| `batch_size` | `int` | `10` | Number of texts to process per batch |
+| `enforce_eager` | `bool` | `True` | Use eager execution mode (local mode) |
+| `vllm_kwargs` | `Optional[Dict[str, Any]]` | `None` | Additional vLLM engine parameters (local mode) |
+| `request_params` | `Optional[Dict[str, Any]]` | `None` | Additional request parameters (remote mode) |
+| `client_params` | `Optional[Dict[str, Any]]` | `None` | OpenAI client configuration (remote mode) |
+
+## Developer Resources
+- View [Cookbook](https://github.com/agno-agi/agno/tree/main/cookbook/knowledge/embedders/vllm_embedder.py)