Add new model configurations and enforce max response length in prompts
This commit is contained in:
12
configs.yaml
12
configs.yaml
@@ -28,6 +28,10 @@ models:
|
|||||||
label: Qwen 3 (4B)
|
label: Qwen 3 (4B)
|
||||||
- name: qwen3:1.7b
|
- name: qwen3:1.7b
|
||||||
label: Qwen 3 (1.7B)
|
label: Qwen 3 (1.7B)
|
||||||
|
- name: qwen3:32b
|
||||||
|
label: Qwen 3 (32B)
|
||||||
|
- name: phi4-mini:3.8b
|
||||||
|
label: Phi 4 mini (3.8b)
|
||||||
|
|
||||||
api:
|
api:
|
||||||
retry_attempts: 3
|
retry_attempts: 3
|
||||||
@@ -40,7 +44,7 @@ api:
|
|||||||
|
|
||||||
agents:
|
agents:
|
||||||
strategy: Conservative
|
strategy: Conservative
|
||||||
team_model: qwen3:8b
|
team_model: qwen3:32b # the agents
|
||||||
team_leader_model: qwen3:8b
|
team_leader_model: qwen3:32b # the team leader
|
||||||
query_analyzer_model: qwen3:8b # query check
|
query_analyzer_model: qwen3:32b # query check
|
||||||
report_generation_model: qwen3:8b # ex predictor
|
report_generation_model: qwen3:32b # ex predictor
|
||||||
|
|||||||
@@ -54,6 +54,7 @@ Detailed Data:
|
|||||||
3. **Always specify the data source** (which API provided the data)
|
3. **Always specify the data source** (which API provided the data)
|
||||||
4. **Report data completeness**: If user asks for 30 days but got 7, state this explicitly
|
4. **Report data completeness**: If user asks for 30 days but got 7, state this explicitly
|
||||||
5. **Current date context**: Remind that data is as of {{CURRENT_DATE}}
|
5. **Current date context**: Remind that data is as of {{CURRENT_DATE}}
|
||||||
|
6. **Max response length**: Do not overcome 100 words
|
||||||
|
|
||||||
**ERROR HANDLING:**
|
**ERROR HANDLING:**
|
||||||
- Tools failed → "Price data unavailable. Error: [details if available]"
|
- Tools failed → "Price data unavailable. Error: [details if available]"
|
||||||
|
|||||||
@@ -64,6 +64,7 @@ Notable Headlines:
|
|||||||
3. **Report data staleness**: If newest article is >3 days old, flag this
|
3. **Report data staleness**: If newest article is >3 days old, flag this
|
||||||
4. **Cite sources**: Mention which news APIs provided the data
|
4. **Cite sources**: Mention which news APIs provided the data
|
||||||
5. **Distinguish sentiment from facts**: Sentiment = your analysis; Facts = article content
|
5. **Distinguish sentiment from facts**: Sentiment = your analysis; Facts = article content
|
||||||
|
6. **Max response length**: Do not overcome 100 words
|
||||||
|
|
||||||
**ERROR HANDLING:**
|
**ERROR HANDLING:**
|
||||||
- No articles found → "No relevant news articles found for [QUERY]"
|
- No articles found → "No relevant news articles found for [QUERY]"
|
||||||
|
|||||||
@@ -70,6 +70,7 @@ Sample Posts (representative):
|
|||||||
3. **Report data staleness**: If newest post is >2 days old, flag this
|
3. **Report data staleness**: If newest post is >2 days old, flag this
|
||||||
4. **Context is key**: Social sentiment ≠ financial advice (mention this if relevant)
|
4. **Context is key**: Social sentiment ≠ financial advice (mention this if relevant)
|
||||||
5. **Distinguish hype from substance**: Note if narratives are speculation vs fact-based
|
5. **Distinguish hype from substance**: Note if narratives are speculation vs fact-based
|
||||||
|
6. **Max response length**: Do not overcome 100 words
|
||||||
|
|
||||||
**ERROR HANDLING:**
|
**ERROR HANDLING:**
|
||||||
- No posts found → "No relevant social discussions found for [QUERY]"
|
- No posts found → "No relevant social discussions found for [QUERY]"
|
||||||
|
|||||||
Reference in New Issue
Block a user