886 lines
77 KiB
YAML
886 lines
77 KiB
YAML
interactions:
|
||
- request:
|
||
headers:
|
||
accept:
|
||
- application/json
|
||
accept-encoding:
|
||
- gzip, deflate, zstd
|
||
connection:
|
||
- keep-alive
|
||
content-length:
|
||
- '114'
|
||
content-type:
|
||
- application/json
|
||
host:
|
||
- localhost:11434
|
||
method: POST
|
||
parsed_body:
|
||
encoding_format: base64
|
||
input:
|
||
- Python is a high-level programming language.
|
||
model: qwen3-embedding:4b
|
||
uri: http://localhost:11434/v1/embeddings
|
||
response:
|
||
headers:
|
||
content-type:
|
||
- application/json
|
||
transfer-encoding:
|
||
- chunked
|
||
parsed_body:
|
||
data:
|
||
- embedding: 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
|
||
index: 0
|
||
object: embedding
|
||
model: qwen3-embedding:4b
|
||
object: list
|
||
usage:
|
||
prompt_tokens: 9
|
||
total_tokens: 9
|
||
status:
|
||
code: 200
|
||
message: OK
|
||
- request:
|
||
headers:
|
||
accept:
|
||
- application/json
|
||
accept-encoding:
|
||
- gzip, deflate, zstd
|
||
connection:
|
||
- keep-alive
|
||
content-length:
|
||
- '5583'
|
||
content-type:
|
||
- application/json
|
||
host:
|
||
- localhost:11434
|
||
method: POST
|
||
parsed_body:
|
||
messages:
|
||
- content: |-
|
||
You are a focused execution agent. Complete the following task using the skills and instructions provided.
|
||
|
||
## Task
|
||
|
||
What is Python?
|
||
|
||
## Skill instructions
|
||
|
||
# RAG
|
||
|
||
You are a RAG assistant with access to a document knowledge base.
|
||
Use your tools to search and answer questions. Never make up information — always use tools to get facts from the knowledge base.
|
||
|
||
## Tools
|
||
|
||
### search
|
||
Search the knowledge base using hybrid search (vector + full-text). Returns ranked results with context-expanded content.
|
||
|
||
Each result includes:
|
||
- `chunk_id` in brackets and rank position (rank 1 = most relevant)
|
||
- Source: document title and section hierarchy
|
||
- Type: content type (paragraph, table, code, list_item, picture)
|
||
- Content: the actual text
|
||
|
||
When a result's Type is `picture`, the corresponding figure may also be attached to the tool response as an image alongside the text. Use the image directly to answer questions about figures, diagrams, charts, screenshots.
|
||
|
||
### list_documents
|
||
List available documents in the knowledge base. Use when the user wants to browse what's available.
|
||
|
||
### get_document
|
||
Retrieve a document by ID, title, or URI. Partial matches work. Use when the user wants the full content of a specific document.
|
||
|
||
### cite
|
||
Register the chunk IDs that ground your answer. Call this BEFORE writing your final answer, with the `chunk_id` values from search results that support each claim. Every answer that uses search results must be backed by `cite`.
|
||
|
||
Use chunk_ids exactly as they appear in the search response — copy the full UUID verbatim. Do not abbreviate, paraphrase, or reconstruct chunk_ids from memory; the tool matches them as opaque strings.
|
||
|
||
## How to answer questions
|
||
|
||
1. Call `search` with relevant keywords from the question
|
||
2. Review the results — they are ordered by relevance (rank 1 = best match)
|
||
3. If needed, search again with different keywords (you have a limited number of searches)
|
||
4. Identify the chunk IDs that support your answer and call `cite` with them
|
||
5. Then write a concise answer based strictly on the cited content
|
||
|
||
You MUST call `cite` with at least one chunk ID before producing your final answer, **unless** you are refusing for lack of information (see below). Answers without citations are considered ungrounded.
|
||
|
||
## Guidelines
|
||
|
||
- Base answers strictly on retrieved content — do not use external knowledge
|
||
- Use the Source and Type metadata to understand context
|
||
- If multiple results are relevant, synthesize them coherently
|
||
- Be concise and direct — avoid elaboration unless asked
|
||
- If the search tool tells you the search limit is reached, stop searching and answer with what you have
|
||
- If the retrieved documents do not directly address the question, say: "I cannot find enough information in the knowledge base to answer this question." Do not guess or infer from tangentially related content. In this refusal case do **not** call `cite` — there is nothing to cite.
|
||
- Do NOT include chunk IDs or UUIDs in your answer text — your answer should read naturally. Use the `cite` tool separately to register citations.
|
||
|
||
## When the user mentions a specific document
|
||
|
||
If the user says "search in [doc]", "find in [doc]", or "answer from [doc]":
|
||
- Use `get_document` or `list_documents` first to identify the document
|
||
- Then search for the topic
|
||
|
||
## When search returns irrelevant results
|
||
|
||
If your first search returns results that clearly don't match the question:
|
||
- Try one more search with different keywords
|
||
- If still irrelevant, report that the knowledge base doesn't contain relevant information
|
||
|
||
## Guidelines
|
||
|
||
- Follow the skill instructions carefully
|
||
- Stay focused on the specific task described above
|
||
- Provide a clear, complete result
|
||
role: system
|
||
- content: What is Python?
|
||
role: user
|
||
model: gpt-oss
|
||
reasoning_effort: high
|
||
stream: true
|
||
stream_options:
|
||
include_usage: true
|
||
temperature: 0.3
|
||
tool_choice: auto
|
||
tools:
|
||
- function:
|
||
description: |-
|
||
Search the knowledge base using hybrid search (vector + full-text).
|
||
|
||
Returns ranked results with content and metadata. When picture
|
||
content is in the result set and the driving skill model is
|
||
vision-capable, picture bytes are attached as ``BinaryContent``
|
||
parts so the model sees figures alongside text.
|
||
name: search
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
limit:
|
||
anyOf:
|
||
- type: integer
|
||
- type: 'null'
|
||
default: null
|
||
description: Maximum number of results.
|
||
query:
|
||
description: The search query.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: List all documents in the knowledge base.
|
||
name: list_documents
|
||
parameters:
|
||
additionalProperties: false
|
||
properties: {}
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: Retrieve a document by ID, title, or URI.
|
||
name: get_document
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
query:
|
||
description: Document ID, title, or URI to look up.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: |-
|
||
Register chunk IDs as citations for your answer.
|
||
|
||
Call this after searching, with the chunk_id values from search
|
||
results that support your answer.
|
||
name: cite
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
chunk_ids:
|
||
description: List of chunk_id values from search results.
|
||
items:
|
||
type: string
|
||
type: array
|
||
required:
|
||
- chunk_ids
|
||
type: object
|
||
type: function
|
||
uri: http://localhost:11434/v1/chat/completions
|
||
response:
|
||
body:
|
||
string: |+
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114310,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"We"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114310,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" need"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114310,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" to"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114310,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" answer"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":":"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" \""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"What"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" is"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" Python"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"?\""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" We"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" must"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" use"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" the"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" knowledge"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" base"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" We"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" need"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" to"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" search"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" Let's"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" search"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" for"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" \""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"Python"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"\""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" or"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" \""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"Python"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" programming"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" language"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"\""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" etc"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","tool_calls":[{"id":"call_c33pjm3l","index":0,"type":"function","function":{"name":"search","arguments":"{\"query\":\"Python programming language\",\"limit\":5}"}}]},"finish_reason":"tool_calls"}]}
|
||
|
||
data: {"id":"chatcmpl-381","object":"chat.completion.chunk","created":1779114311,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[],"usage":{"prompt_tokens":1077,"completion_tokens":65,"total_tokens":1142}}
|
||
|
||
data: [DONE]
|
||
|
||
headers:
|
||
content-type:
|
||
- text/event-stream
|
||
transfer-encoding:
|
||
- chunked
|
||
status:
|
||
code: 200
|
||
message: OK
|
||
- request:
|
||
headers:
|
||
accept:
|
||
- application/json
|
||
accept-encoding:
|
||
- gzip, deflate, zstd
|
||
connection:
|
||
- keep-alive
|
||
content-length:
|
||
- '97'
|
||
content-type:
|
||
- application/json
|
||
host:
|
||
- localhost:11434
|
||
method: POST
|
||
parsed_body:
|
||
encoding_format: base64
|
||
input:
|
||
- Python programming language
|
||
model: qwen3-embedding:4b
|
||
uri: http://localhost:11434/v1/embeddings
|
||
response:
|
||
headers:
|
||
content-type:
|
||
- application/json
|
||
transfer-encoding:
|
||
- chunked
|
||
parsed_body:
|
||
data:
|
||
- embedding: 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
|
||
index: 0
|
||
object: embedding
|
||
model: qwen3-embedding:4b
|
||
object: list
|
||
usage:
|
||
prompt_tokens: 4
|
||
total_tokens: 4
|
||
status:
|
||
code: 200
|
||
message: OK
|
||
- request:
|
||
headers:
|
||
accept:
|
||
- application/json
|
||
accept-encoding:
|
||
- gzip, deflate, zstd
|
||
connection:
|
||
- keep-alive
|
||
content-length:
|
||
- '6126'
|
||
content-type:
|
||
- application/json
|
||
host:
|
||
- localhost:11434
|
||
method: POST
|
||
parsed_body:
|
||
messages:
|
||
- content: |-
|
||
You are a focused execution agent. Complete the following task using the skills and instructions provided.
|
||
|
||
## Task
|
||
|
||
What is Python?
|
||
|
||
## Skill instructions
|
||
|
||
# RAG
|
||
|
||
You are a RAG assistant with access to a document knowledge base.
|
||
Use your tools to search and answer questions. Never make up information — always use tools to get facts from the knowledge base.
|
||
|
||
## Tools
|
||
|
||
### search
|
||
Search the knowledge base using hybrid search (vector + full-text). Returns ranked results with context-expanded content.
|
||
|
||
Each result includes:
|
||
- `chunk_id` in brackets and rank position (rank 1 = most relevant)
|
||
- Source: document title and section hierarchy
|
||
- Type: content type (paragraph, table, code, list_item, picture)
|
||
- Content: the actual text
|
||
|
||
When a result's Type is `picture`, the corresponding figure may also be attached to the tool response as an image alongside the text. Use the image directly to answer questions about figures, diagrams, charts, screenshots.
|
||
|
||
### list_documents
|
||
List available documents in the knowledge base. Use when the user wants to browse what's available.
|
||
|
||
### get_document
|
||
Retrieve a document by ID, title, or URI. Partial matches work. Use when the user wants the full content of a specific document.
|
||
|
||
### cite
|
||
Register the chunk IDs that ground your answer. Call this BEFORE writing your final answer, with the `chunk_id` values from search results that support each claim. Every answer that uses search results must be backed by `cite`.
|
||
|
||
Use chunk_ids exactly as they appear in the search response — copy the full UUID verbatim. Do not abbreviate, paraphrase, or reconstruct chunk_ids from memory; the tool matches them as opaque strings.
|
||
|
||
## How to answer questions
|
||
|
||
1. Call `search` with relevant keywords from the question
|
||
2. Review the results — they are ordered by relevance (rank 1 = best match)
|
||
3. If needed, search again with different keywords (you have a limited number of searches)
|
||
4. Identify the chunk IDs that support your answer and call `cite` with them
|
||
5. Then write a concise answer based strictly on the cited content
|
||
|
||
You MUST call `cite` with at least one chunk ID before producing your final answer, **unless** you are refusing for lack of information (see below). Answers without citations are considered ungrounded.
|
||
|
||
## Guidelines
|
||
|
||
- Base answers strictly on retrieved content — do not use external knowledge
|
||
- Use the Source and Type metadata to understand context
|
||
- If multiple results are relevant, synthesize them coherently
|
||
- Be concise and direct — avoid elaboration unless asked
|
||
- If the search tool tells you the search limit is reached, stop searching and answer with what you have
|
||
- If the retrieved documents do not directly address the question, say: "I cannot find enough information in the knowledge base to answer this question." Do not guess or infer from tangentially related content. In this refusal case do **not** call `cite` — there is nothing to cite.
|
||
- Do NOT include chunk IDs or UUIDs in your answer text — your answer should read naturally. Use the `cite` tool separately to register citations.
|
||
|
||
## When the user mentions a specific document
|
||
|
||
If the user says "search in [doc]", "find in [doc]", or "answer from [doc]":
|
||
- Use `get_document` or `list_documents` first to identify the document
|
||
- Then search for the topic
|
||
|
||
## When search returns irrelevant results
|
||
|
||
If your first search returns results that clearly don't match the question:
|
||
- Try one more search with different keywords
|
||
- If still irrelevant, report that the knowledge base doesn't contain relevant information
|
||
|
||
## Guidelines
|
||
|
||
- Follow the skill instructions carefully
|
||
- Stay focused on the specific task described above
|
||
- Provide a clear, complete result
|
||
role: system
|
||
- content: What is Python?
|
||
role: user
|
||
- content: null
|
||
reasoning: 'We need to answer: "What is Python?" We must use the knowledge base. We need to search. Let''s search
|
||
for "Python" or "Python programming language" etc.'
|
||
role: assistant
|
||
tool_calls:
|
||
- function:
|
||
arguments: '{"query":"Python programming language","limit":5}'
|
||
name: search
|
||
id: call_c33pjm3l
|
||
type: function
|
||
- content: |-
|
||
[ae8a228f-c5f8-43bd-9dbd-582b2e5e27a5] [rank 1 of 1]
|
||
Type: text
|
||
Content:
|
||
Python is a high-level programming language.
|
||
role: tool
|
||
tool_call_id: call_c33pjm3l
|
||
model: gpt-oss
|
||
reasoning_effort: high
|
||
stream: true
|
||
stream_options:
|
||
include_usage: true
|
||
temperature: 0.3
|
||
tool_choice: auto
|
||
tools:
|
||
- function:
|
||
description: |-
|
||
Search the knowledge base using hybrid search (vector + full-text).
|
||
|
||
Returns ranked results with content and metadata. When picture
|
||
content is in the result set and the driving skill model is
|
||
vision-capable, picture bytes are attached as ``BinaryContent``
|
||
parts so the model sees figures alongside text.
|
||
name: search
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
limit:
|
||
anyOf:
|
||
- type: integer
|
||
- type: 'null'
|
||
default: null
|
||
description: Maximum number of results.
|
||
query:
|
||
description: The search query.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: List all documents in the knowledge base.
|
||
name: list_documents
|
||
parameters:
|
||
additionalProperties: false
|
||
properties: {}
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: Retrieve a document by ID, title, or URI.
|
||
name: get_document
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
query:
|
||
description: Document ID, title, or URI to look up.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: |-
|
||
Register chunk IDs as citations for your answer.
|
||
|
||
Call this after searching, with the chunk_id values from search
|
||
results that support your answer.
|
||
name: cite
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
chunk_ids:
|
||
description: List of chunk_id values from search results.
|
||
items:
|
||
type: string
|
||
type: array
|
||
required:
|
||
- chunk_ids
|
||
type: object
|
||
type: function
|
||
uri: http://localhost:11434/v1/chat/completions
|
||
response:
|
||
body:
|
||
string: |+
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"We"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" have"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" a"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" result"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":":"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" chunk"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"_id"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" ae"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"8"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"a"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"228"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"f"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"-c"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"5"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"f"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"8"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"-"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"43"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"bd"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"-"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"9"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"db"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"d"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"-"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"582"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"b"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"2"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"e"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"5"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"e"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"27"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"a"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"5"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":","},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" content"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":":"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" \""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"Python"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" is"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" a"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" high"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"-level"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" programming"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" language"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":".\""},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" That"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" is"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" enough"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" We"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" need"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" to"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114312,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":" cite"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114313,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114313,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"","tool_calls":[{"id":"call_xtrtxg84","index":0,"type":"function","function":{"name":"cite","arguments":"{\"chunk_ids\":[\"ae8a228f-c5f8-43bd-9dbd-582b2e5e27a5\"]}"}}]},"finish_reason":"tool_calls"}]}
|
||
|
||
data: {"id":"chatcmpl-713","object":"chat.completion.chunk","created":1779114313,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[],"usage":{"prompt_tokens":1202,"completion_tokens":105,"total_tokens":1307}}
|
||
|
||
data: [DONE]
|
||
|
||
headers:
|
||
content-type:
|
||
- text/event-stream
|
||
transfer-encoding:
|
||
- chunked
|
||
status:
|
||
code: 200
|
||
message: OK
|
||
- request:
|
||
headers:
|
||
accept:
|
||
- application/json
|
||
accept-encoding:
|
||
- gzip, deflate, zstd
|
||
connection:
|
||
- keep-alive
|
||
content-length:
|
||
- '6573'
|
||
content-type:
|
||
- application/json
|
||
host:
|
||
- localhost:11434
|
||
method: POST
|
||
parsed_body:
|
||
messages:
|
||
- content: |-
|
||
You are a focused execution agent. Complete the following task using the skills and instructions provided.
|
||
|
||
## Task
|
||
|
||
What is Python?
|
||
|
||
## Skill instructions
|
||
|
||
# RAG
|
||
|
||
You are a RAG assistant with access to a document knowledge base.
|
||
Use your tools to search and answer questions. Never make up information — always use tools to get facts from the knowledge base.
|
||
|
||
## Tools
|
||
|
||
### search
|
||
Search the knowledge base using hybrid search (vector + full-text). Returns ranked results with context-expanded content.
|
||
|
||
Each result includes:
|
||
- `chunk_id` in brackets and rank position (rank 1 = most relevant)
|
||
- Source: document title and section hierarchy
|
||
- Type: content type (paragraph, table, code, list_item, picture)
|
||
- Content: the actual text
|
||
|
||
When a result's Type is `picture`, the corresponding figure may also be attached to the tool response as an image alongside the text. Use the image directly to answer questions about figures, diagrams, charts, screenshots.
|
||
|
||
### list_documents
|
||
List available documents in the knowledge base. Use when the user wants to browse what's available.
|
||
|
||
### get_document
|
||
Retrieve a document by ID, title, or URI. Partial matches work. Use when the user wants the full content of a specific document.
|
||
|
||
### cite
|
||
Register the chunk IDs that ground your answer. Call this BEFORE writing your final answer, with the `chunk_id` values from search results that support each claim. Every answer that uses search results must be backed by `cite`.
|
||
|
||
Use chunk_ids exactly as they appear in the search response — copy the full UUID verbatim. Do not abbreviate, paraphrase, or reconstruct chunk_ids from memory; the tool matches them as opaque strings.
|
||
|
||
## How to answer questions
|
||
|
||
1. Call `search` with relevant keywords from the question
|
||
2. Review the results — they are ordered by relevance (rank 1 = best match)
|
||
3. If needed, search again with different keywords (you have a limited number of searches)
|
||
4. Identify the chunk IDs that support your answer and call `cite` with them
|
||
5. Then write a concise answer based strictly on the cited content
|
||
|
||
You MUST call `cite` with at least one chunk ID before producing your final answer, **unless** you are refusing for lack of information (see below). Answers without citations are considered ungrounded.
|
||
|
||
## Guidelines
|
||
|
||
- Base answers strictly on retrieved content — do not use external knowledge
|
||
- Use the Source and Type metadata to understand context
|
||
- If multiple results are relevant, synthesize them coherently
|
||
- Be concise and direct — avoid elaboration unless asked
|
||
- If the search tool tells you the search limit is reached, stop searching and answer with what you have
|
||
- If the retrieved documents do not directly address the question, say: "I cannot find enough information in the knowledge base to answer this question." Do not guess or infer from tangentially related content. In this refusal case do **not** call `cite` — there is nothing to cite.
|
||
- Do NOT include chunk IDs or UUIDs in your answer text — your answer should read naturally. Use the `cite` tool separately to register citations.
|
||
|
||
## When the user mentions a specific document
|
||
|
||
If the user says "search in [doc]", "find in [doc]", or "answer from [doc]":
|
||
- Use `get_document` or `list_documents` first to identify the document
|
||
- Then search for the topic
|
||
|
||
## When search returns irrelevant results
|
||
|
||
If your first search returns results that clearly don't match the question:
|
||
- Try one more search with different keywords
|
||
- If still irrelevant, report that the knowledge base doesn't contain relevant information
|
||
|
||
## Guidelines
|
||
|
||
- Follow the skill instructions carefully
|
||
- Stay focused on the specific task described above
|
||
- Provide a clear, complete result
|
||
role: system
|
||
- content: What is Python?
|
||
role: user
|
||
- content: null
|
||
reasoning: 'We need to answer: "What is Python?" We must use the knowledge base. We need to search. Let''s search
|
||
for "Python" or "Python programming language" etc.'
|
||
role: assistant
|
||
tool_calls:
|
||
- function:
|
||
arguments: '{"query":"Python programming language","limit":5}'
|
||
name: search
|
||
id: call_c33pjm3l
|
||
type: function
|
||
- content: |-
|
||
[ae8a228f-c5f8-43bd-9dbd-582b2e5e27a5] [rank 1 of 1]
|
||
Type: text
|
||
Content:
|
||
Python is a high-level programming language.
|
||
role: tool
|
||
tool_call_id: call_c33pjm3l
|
||
- content: null
|
||
reasoning: 'We have a result: chunk_id ae8a228f-c5f8-43bd-9dbd-582b2e5e27a5, content: "Python is a high-level programming
|
||
language." That is enough. We need to cite.'
|
||
role: assistant
|
||
tool_calls:
|
||
- function:
|
||
arguments: '{"chunk_ids":["ae8a228f-c5f8-43bd-9dbd-582b2e5e27a5"]}'
|
||
name: cite
|
||
id: call_xtrtxg84
|
||
type: function
|
||
- content: Registered 1 citation(s).
|
||
role: tool
|
||
tool_call_id: call_xtrtxg84
|
||
model: gpt-oss
|
||
reasoning_effort: high
|
||
stream: true
|
||
stream_options:
|
||
include_usage: true
|
||
temperature: 0.3
|
||
tool_choice: auto
|
||
tools:
|
||
- function:
|
||
description: |-
|
||
Search the knowledge base using hybrid search (vector + full-text).
|
||
|
||
Returns ranked results with content and metadata. When picture
|
||
content is in the result set and the driving skill model is
|
||
vision-capable, picture bytes are attached as ``BinaryContent``
|
||
parts so the model sees figures alongside text.
|
||
name: search
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
limit:
|
||
anyOf:
|
||
- type: integer
|
||
- type: 'null'
|
||
default: null
|
||
description: Maximum number of results.
|
||
query:
|
||
description: The search query.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: List all documents in the knowledge base.
|
||
name: list_documents
|
||
parameters:
|
||
additionalProperties: false
|
||
properties: {}
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: Retrieve a document by ID, title, or URI.
|
||
name: get_document
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
query:
|
||
description: Document ID, title, or URI to look up.
|
||
type: string
|
||
required:
|
||
- query
|
||
type: object
|
||
type: function
|
||
- function:
|
||
description: |-
|
||
Register chunk IDs as citations for your answer.
|
||
|
||
Call this after searching, with the chunk_id values from search
|
||
results that support your answer.
|
||
name: cite
|
||
parameters:
|
||
additionalProperties: false
|
||
properties:
|
||
chunk_ids:
|
||
description: List of chunk_id values from search results.
|
||
items:
|
||
type: string
|
||
type: array
|
||
required:
|
||
- chunk_ids
|
||
type: object
|
||
type: function
|
||
uri: http://localhost:11434/v1/chat/completions
|
||
response:
|
||
body:
|
||
string: |+
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"Python"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" is"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" high"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"‑"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"level"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" programming"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" language"},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop"}]}
|
||
|
||
data: {"id":"chatcmpl-985","object":"chat.completion.chunk","created":1779114314,"model":"gpt-oss","system_fingerprint":"fp_ollama","choices":[],"usage":{"prompt_tokens":1324,"completion_tokens":13,"total_tokens":1337}}
|
||
|
||
data: [DONE]
|
||
|
||
headers:
|
||
content-type:
|
||
- text/event-stream
|
||
transfer-encoding:
|
||
- chunked
|
||
status:
|
||
code: 200
|
||
message: OK
|
||
version: 1
|
||
...
|