| --- |
| library_name: transformers |
| pipeline_tag: text-generation |
| tags: |
| - research-assistant |
| - tool-use |
| - citations |
| license: apache-2.0 |
| --- |
| |
| # Meridian |
|
|
| Meridian is a research-focused chat model built to work inside an app with live search, browsing, and source-reading tools. |
|
|
| It is designed for assistants that need to: |
|
|
| - search the web before answering current or source-sensitive questions |
| - read retrieved pages or documents |
| - cite sources inline |
| - answer concisely instead of rambling |
| - separate tool calls from final responses |
|
|
| Meridian is not meant to be used as a plain offline chatbot for factual questions. It works best when your application gives it tools such as search, page open, document retrieval, or database lookup. |
|
|
| ## How it behaves |
|
|
| For questions that need fresh or grounded information, Meridian can emit tool calls like: |
|
|
| ```xml |
| <call> |
| {"tool":"browser.search","input":{"query":"latest OpenAI ChatGPT model announcement"}} |
| </call> |
| ``` |
|
|
| After your app executes the tool and returns source text, Meridian is expected to answer with citations: |
|
|
| ```xml |
| <response> |
| OpenAI announced GPT-5.2 as a newer frontier model for ChatGPT and API users, highlighting stronger reasoning, long-context understanding, coding, and vision capabilities. [source:1] |
| </response> |
| ``` |
|
|
| Your app is responsible for actually running the tools. The model only decides when and how to call them. |
|
|
| ## Recommended app loop |
|
|
| 1. Send the user message and system prompt to Meridian. |
| 2. Watch the generation for `<call>...</call>` blocks. |
| 3. Parse the JSON inside each call. |
| 4. Execute the matching tool in your app. |
| 5. Feed the tool result back to the model as source text. |
| 6. Ask the model for the final `<response>`. |
|
|
| Example source block: |
|
|
| ```xml |
| <tool_result> |
| {"source_id":1,"title":"Example article","url":"https://example.com","text":"Relevant page text..."} |
| </tool_result> |
| ``` |
|
|
| ## Prompt style |
|
|
| A good system prompt is direct and tool-aware: |
|
|
| ```text |
| You are Meridian, a source-grounded research assistant. |
| Use browser.search when current or factual information is needed. |
| Use browser.open to read promising sources. |
| Answer concisely and cite sources inline as [source:1], [source:2]. |
| If sources do not support a claim, say so. |
| Do not invent citations. |
| ``` |
|
|
| ## What Meridian is good at |
|
|
| - research assistant workflows |
| - live search and browsing agents |
| - citation-style answers |
| - tool-call formatting |
| - short factual summaries from provided sources |
| - app-integrated RAG experiences |
|
|
| ## What Meridian is not |
|
|
| - a search engine by itself |
| - a guarantee of truth without retrieval |
| - a replacement for source filtering or ranking |
| - a model that can browse unless your app gives it browsing tools |
|
|
| ## Safety and reliability notes |
|
|
| Meridian should be used with source validation in your application. For best results: |
|
|
| - prefer trusted domains when ranking search results |
| - open and read sources before asking for the final answer |
| - require citations for factual claims |
| - show source links to users |
| - handle tool errors explicitly |
| - avoid letting the model invent source IDs |
|
|
| ## Loading |
|
|
| This repository contains a merged Transformers model. Load it with `transformers`: |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_id = "Pharos-ai/Meridian" |
| |
| tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) |
| model = AutoModelForCausalLM.from_pretrained( |
| model_id, |
| torch_dtype="auto", |
| device_map="auto", |
| trust_remote_code=True, |
| ) |
| ``` |
|
|
| For production use, connect Meridian to your own search, browser, and retrieval tools. |
