[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

examples/offline_inference_embedding.py

@@ -0,0 +1,17 @@
+from vllm import LLM
+
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+
+# Create an LLM.
+model = LLM(model="intfloat/e5-mistral-7b-instruct", enforce_eager=True)
+# Generate embedding. The output is a list of EmbeddingRequestOutputs.
+outputs = model.encode(prompts)
+# Print the outputs.
+for output in outputs:
+    print(output.outputs.embedding)  # list of 4096 floats

examples/openai_embedding_client.py

@@ -0,0 +1,23 @@
+from openai import OpenAI
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+responses = client.embeddings.create(input=[
+    "Hello my name is",
+    "The best thing about vLLM is that it supports many different models"
+],
+                                     model=model)
+
+for data in responses.data:
+    print(data.embedding)  # list of float of len 4096