Instructions to use chromadb/context-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chromadb/context-1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="chromadb/context-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chromadb/context-1")
model = AutoModelForCausalLM.from_pretrained("chromadb/context-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chromadb/context-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chromadb/context-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chromadb/context-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chromadb/context-1

SGLang

How to use chromadb/context-1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "chromadb/context-1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chromadb/context-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "chromadb/context-1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chromadb/context-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chromadb/context-1 with Docker Model Runner:
```
docker model run hf.co/chromadb/context-1
```

Self-editing context for long-horizon retrieval: practical deployment questions

by O96a - opened Mar 30

Discussion

O96a

Mar 30

The self-editing context mechanism with 0.94 prune accuracy addresses a core pain point in production RAG systems — context bloat degrading retrieval quality over long reasoning chains. Query decomposition + parallel tool calling (2.56 calls/turn) is an elegant efficiency win.

A few deployment questions:

The 10x faster inference speed claim — is that comparing against frontier models like GPT-4o running full retrieval loops, or against smaller specialized retrievers? For a 20B MoE, I'd expect significant latency gains, but curious about the baseline.
The staged curriculum training (SFT + RL with CISPO) — is there a threshold where the RL fine-tuning becomes critical? In my experience with retrieval agents, SFT-only models often struggle with strategic context pruning.
The harness requirement is notable. For teams building with Context-1 before the harness release, what's the minimum scaffold needed to get functional retrieval? Is it primarily the token budget manager and deduplication layer?

Looking forward to the harness release — self-editing context is the right abstraction for agentic RAG pipelines.

hammadtime

chroma org Mar 30

Its comparing to models such as Opus4.5 and GPT5.2. We benchmarked on a single B200 MXFP4 checkpoint and it is even faster with speculative decoding.
We didn't ablate RL vs no-RL rigorously. But I can say RL was necessary here for performance.
Thats about right, we should have the harness ready in open source this week and you can also use it today hosted - https://www.trychroma.com/products/agent

a-huk

Mar 30

For speculative decoding you used nvidia/gpt-oss-120b-Eagle3-long-context ?

Its comparing to models such as Opus4.5 and GPT5.2. We benchmarked on a single B200 MXFP4 checkpoint and it is even faster with speculative decoding.

We didn't ablate RL vs no-RL rigorously. But I can say RL was necessary here for performance.

Thats about right, we should have the harness ready in open source this week and you can also use it today hosted - https://www.trychroma.com/products/agent

lxww301

Apr 13

Its comparing to models such as Opus4.5 and GPT5.2. We benchmarked on a single B200 MXFP4 checkpoint and it is even faster with speculative decoding.

We didn't ablate RL vs no-RL rigorously. But I can say RL was necessary here for performance.

Thats about right, we should have the harness ready in open source this week and you can also use it today hosted - https://www.trychroma.com/products/agent

Could you share any updates on the timeline for open-sourcing the harness?

pirola

Apr 14

Can't wait for the open source harness to be available!

pirola

Apr 15

@hammadtime any updates on the open source harness?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment