Feat: add meta data filter. (#9405)

### What problem does this PR solve?

#8531 
#7417 
#6761 
#6573
#6477

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

api/db/services/dialog_service.py

@@ -30,6 +30,7 @@ from api import settings
 from api.db import LLMType, ParserType, StatusEnum
 from api.db.db_models import DB, Dialog
 from api.db.services.common_service import CommonService
+from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.langfuse_service import TenantLangfuseService
 from api.db.services.llm_service import LLMBundle, TenantLLMService
@@ -38,6 +39,7 @@ from rag.app.resume import forbidden_select_fields4resume
 from rag.app.tag import label_question
 from rag.nlp.search import index_name
 from rag.prompts import chunks_format, citation_prompt, cross_languages, full_question, kb_prompt, keyword_extraction, message_fit_in
+from rag.prompts.prompts import gen_meta_filter
 from rag.utils import num_tokens_from_string, rmSpace
 from rag.utils.tavily_conn import Tavily
 
@@ -250,6 +252,46 @@ def repair_bad_citation_formats(answer: str, kbinfos: dict, idx: set):
     return answer, idx
 
 
+def meta_filter(metas: dict, filters: list[dict]):
+    doc_ids = []
+    def filter_out(v2docs, operator, value):
+        nonlocal doc_ids
+        for input,docids in v2docs.items():
+            try:
+                input = float(input)
+                value = float(value)
+            except Exception:
+                input = str(input)
+                value = str(value)
+
+            for conds in [
+                    (operator == "contains", str(value).lower() in str(input).lower()),
+                    (operator == "not contains", str(value).lower() not in str(input).lower()),
+                    (operator == "start with", str(input).lower().startswith(str(value).lower())),
+                    (operator == "end with", str(input).lower().endswith(str(value).lower())),
+                    (operator == "empty", not input),
+                    (operator == "not empty", input),
+                    (operator == "=", input == value),
+                    (operator == "≠", input != value),
+                    (operator == ">", input > value),
+                    (operator == "<", input < value),
+                    (operator == "≥", input >= value),
+                    (operator == "≤", input <= value),
+                ]:
+                try:
+                    if all(conds):
+                        doc_ids.extend(docids)
+                except Exception:
+                    pass
+
+    for k, v2docs in metas.items():
+        for f in filters:
+            if k != f["key"]:
+                continue
+            filter_out(v2docs, f["op"], f["value"])
+    return doc_ids
+
+
 def chat(dialog, messages, stream=True, **kwargs):
     assert messages[-1]["role"] == "user", "The last content of this conversation is not from user."
     if not dialog.kb_ids and not dialog.prompt_config.get("tavily_api_key"):
@@ -287,9 +329,10 @@ def chat(dialog, messages, stream=True, **kwargs):
 
     retriever = settings.retrievaler
     questions = [m["content"] for m in messages if m["role"] == "user"][-3:]
-    attachments = kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None
+    attachments = kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else []
     if "doc_ids" in messages[-1]:
         attachments = messages[-1]["doc_ids"]
+
     prompt_config = dialog.prompt_config
     field_map = KnowledgebaseService.get_field_map(dialog.kb_ids)
     # try to use sql if field mapping is good to go
@@ -316,6 +359,14 @@ def chat(dialog, messages, stream=True, **kwargs):
     if prompt_config.get("cross_languages"):
         questions = [cross_languages(dialog.tenant_id, dialog.llm_id, questions[0], prompt_config["cross_languages"])]
 
+    if dialog.meta_data_filter:
+        metas = DocumentService.get_meta_by_kbs(dialog.kb_ids)
+        if dialog.meta_data_filter.get("method") == "auto":
+            filters = gen_meta_filter(chat_mdl, metas, questions[-1])
+            attachments.extend(meta_filter(metas, filters))
+        elif dialog.meta_data_filter.get("method") == "manual":
+            attachments.extend(meta_filter(metas, dialog.meta_data_filter["manual"]))
+
     if prompt_config.get("keyword", False):
         questions[-1] += keyword_extraction(chat_mdl, questions[-1])